Trending repositories for topic interpretability

A game theoretic approach to explain the output of any machine learning model.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

ReFT: Representation Finetuning for Language Models

A curated list of awesome responsible machine learning resources.

Shapley Interactions for Machine Learning

The nnsight package enables interpreting and manipulating the internals of deep learned models.

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libr...

A JAX research toolkit for building, editing, and visualizing neural networks.

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

Fit interpretable models. Explain blackbox machine learning.

Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction - CVPR 2024

Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers

Shapley Interactions for Machine Learning

Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction - CVPR 2024

The nnsight package enables interpreting and manipulating the internals of deep learned models.

ReFT: Representation Finetuning for Language Models

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libr...

Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions

A curated list of awesome responsible machine learning resources.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

A JAX research toolkit for building, editing, and visualizing neural networks.

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

A game theoretic approach to explain the output of any machine learning model.

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

Fit interpretable models. Explain blackbox machine learning.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

A game theoretic approach to explain the output of any machine learning model.

ReFT: Representation Finetuning for Language Models

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers

Model interpretability and understanding for PyTorch

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libr...

Shapley Interactions for Machine Learning

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

A curated list of awesome responsible machine learning resources.

The nnsight package enables interpreting and manipulating the internals of deep learned models.

A JAX research toolkit for building, editing, and visualizing neural networks.

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions

Fit interpretable models. Explain blackbox machine learning.

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.

Monet: Mixture of Monosemantic Experts for Transformers

Generating and validating natural-language explanations.

For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.

[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers

Shapley Interactions for Machine Learning

Monet: Mixture of Monosemantic Experts for Transformers

Generating and validating natural-language explanations.

ReFT: Representation Finetuning for Language Models

For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.

The nnsight package enables interpreting and manipulating the internals of deep learned models.

The code of NeurIPS 2021 paper "Scalable Rule-Based Representation Learning for Interpretable Classification" and TPAMI paper "Learning Interpretable Rules for Scalable Data Representation and Classif...

Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction - CVPR 2024

[NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libr...

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions

Awesome Resources for Advanced Computer Vision Topics

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

A curated list of awesome Fairness in AI resources

Interpretability for sequence generation models 🐛 🔍

A JAX research toolkit for building, editing, and visualizing neural networks.

Model interpretability and understanding for PyTorch

Monet: Mixture of Monosemantic Experts for Transformers

A game theoretic approach to explain the output of any machine learning model.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

ReFT: Representation Finetuning for Language Models

Model interpretability and understanding for PyTorch

Shapley Interactions for Machine Learning

[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libr...

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

The nnsight package enables interpreting and manipulating the internals of deep learned models.

Fit interpretable models. Explain blackbox machine learning.

Monet: Mixture of Monosemantic Experts for Transformers

A curated list of awesome responsible machine learning resources.

A JAX research toolkit for building, editing, and visualizing neural networks.

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions

A collection of research materials on explainable AI/ML

For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

moDel Agnostic Language for Exploration and eXplanation

Monet: Mixture of Monosemantic Experts for Transformers

[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers

For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.

Shapley Interactions for Machine Learning

Code for the paper "Aligning LLM Agents by Learning Latent Preference from User Edits".

CausalGym: Benchmarking causal interpretability methods on linguistic tasks

The code of NeurIPS 2021 paper "Scalable Rule-Based Representation Learning for Interpretable Classification" and TPAMI paper "Learning Interpretable Rules for Scalable Data Representation and Classif...

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

Clinically-Interpretable Radiomics [MICCAI'22, CMPB'21]

Generating and validating natural-language explanations.

ReFT: Representation Finetuning for Language Models

ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"

[NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct

[NeurIPS 2024] Official implementation of the paper "MambaLRP: Explaining Selective State Space Sequence Models".

The nnsight package enables interpreting and manipulating the internals of deep learned models.

TrustyAI Explainability Toolkit

A toolkit for quantitative evaluation of data attribution methods.

Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction - CVPR 2024

Time series explainability via self-supervised model behavior consistency

Python library to explain Tree Ensemble models (TE) like XGBoost, using a rule list.

A JAX research toolkit for building, editing, and visualizing neural networks.

ReFT: Representation Finetuning for Language Models

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

[NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct

Decomposing and Editing Predictions by Modeling Model Computation

[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers

For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.

A toolkit for quantitative evaluation of data attribution methods.

Monet: Mixture of Monosemantic Experts for Transformers

An attribution library for LLMs

This is the official repository for HypoGeniC (Hypothesis Generation in Context), which is an automated, data-driven tool that leverages large language models to generate hypothesis for open-domain re...

Evaluate interpretability methods on localizing and disentangling concepts in LLMs.

[NeurIPS 2024] Official implementation of the paper "MambaLRP: Explaining Selective State Space Sequence Models".

ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"

Code for the paper "Aligning LLM Agents by Learning Latent Preference from User Edits".

Increase interpretability of your models!

Universal Neurons in GPT2 Language Models

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

A game theoretic approach to explain the output of any machine learning model.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

A JAX research toolkit for building, editing, and visualizing neural networks.

ReFT: Representation Finetuning for Language Models

Model interpretability and understanding for PyTorch

Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions

A curated list of awesome responsible machine learning resources.

Fit interpretable models. Explain blackbox machine learning.

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

The nnsight package enables interpreting and manipulating the internals of deep learned models.

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libr...

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

A collection of research materials on explainable AI/ML

Shapley Interactions for Machine Learning

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

Algorithms for explaining machine learning models

Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).

XAI - An eXplainability toolbox for machine learning

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

The nnsight package enables interpreting and manipulating the internals of deep learned models.

Shapley Interactions for Machine Learning

Decomposing and Editing Predictions by Modeling Model Computation

A list of (post-hoc) XAI for time series

[NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct

Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions

Universal Neurons in GPT2 Language Models

Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction - CVPR 2024

Monet: Mixture of Monosemantic Experts for Transformers

Time series explainability via self-supervised model behavior consistency

Scikit-learn friendly library to interpret, and prompt-engineer text datasets using large language models.

Wanna know what your model sees? Here's a package for applying EigenCAM on the new YOLO V8 model

TrustyAI Explainability Toolkit

Sparse and discrete interpretability tool for neural networks

This repository introduces MentaLLaMA, the first open-source instruction following large language model for interpretable mental health analysis.

Tree prompting: easy-to-use scikit-learn interface for improved prompting.

Code for paper: Are Large Language Models Post Hoc Explainers?

Python library to explain Tree Ensemble models (TE) like XGBoost, using a rule list.

Generating and validating natural-language explanations.