17 results found Sort:

stanfordnlp
pyvene stanfordnlp
82
730
apache-2.0
8
Stanford NLP Python library for understanding and improving PyTorch models via interventions
intervention interpretability activation-patching activation-intervention mechanistic-interpretability
Created 2023-02-06
687 commits to main branch, last one 2 days ago
ruizheliUOA
Awesome-Interpretability-in-Large-Language-Models ruizheliUOA
21
335
cc0-1.0
6
This repository collects all relevant resources about interpretability in LLMs
sparse-autoencoder dictionary-learning mechanistic-interpretability interpretability-and-explainability
Created 2024-06-30
56 commits to main branch, last one 5 months ago
MadryLab
modelcomponents MadryLab
8
138
mit
3
Decomposing and Editing Predictions by Modeling Model Computation
pytorch attribution model-editing interpretability mechanistic-interpretability
Created 2024-04-17
12 commits to main branch, last one 10 months ago
OpenMOSS
Language-Model-SAEs OpenMOSS
12
106
unknown
5
For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
interpretability sparse-dictionary sparse-autoencoders mechanistic-interpretability
Created 2024-03-19
577 commits to main branch, last one about a month ago
steering-vectors
steering-vectors steering-vectors
8
94
mit
1
Steering vectors for transformer language models in Pytorch / Huggingface
ai gpt nlp pytorch huggingface representation-engineering mechanistic-interpretability
Created 2024-01-18
68 commits to main branch, last one about a month ago
pauljblazek
deepdistilling pauljblazek
7
85
other
3
Mechanistically interpretable neurosymbolic AI (Nature Comput Sci 2024): losslessly compressing NNs to computer code and discovering new algorithms which generalize out-of-distribution and outperform ...
distilling interpretable neurosymbolic explainable-ai domain-adaptation program-synthesis model-distillation knowledge-distillation inductive-logic-programming mechanistic-interpretability out-of-distribution-generalization
Created 2024-01-13
5 commits to main branch, last one about a year ago
jbloomAus
DecisionTransformerInterpretability jbloomAus
20
79
mit
3
Interpreting how transformers simulate agents performing RL tasks
reinforcement-learning mechanistic-interpretability
Created 2022-12-17
725 commits to main branch, last one about a year ago
epfl-dlab
llm-latent-language epfl-dlab
16
73
unknown
3
Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".
llm llama2 multilingual-nlp mechanistic-interpretability
Created 2024-02-16
24 commits to main branch, last one about a year ago
apartresearch
interpretability-starter apartresearch
2
69
unknown
0
🧠 Starter templates for doing interpretability research
alignment-jam interpretability interpretability-jam mechanistic-interpretability
Created 2022-10-31
17 commits to main branch, last one about a year ago
stanfordnlp
axbench stanfordnlp
5
63
apache-2.0
3
Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
intervention llm-steering interpretability large-language-models mechanistic-interpretability
Created 2024-08-07
399 commits to main branch, last one 13 days ago
taufeeque9
codebook-features taufeeque9
3
62
mit
4
Sparse and discrete interpretability tool for neural networks
codebook features transformers language-model interpretability mechanistic-interpretability
Created 2022-12-13
20 commits to main branch, last one about a year ago
wesg52
sparse-probing-paper wesg52
11
55
mit
2
Sparse probing paper full code.
ai-safety ai-alignment interpretability mechanistic-interpretability
Created 2023-05-02
5 commits to main branch, last one about a year ago
microsoft
automated-brain-explanations microsoft
6
51
mit
6
Generating and validating natural-language explanations for the brain.
gpt xai fmri gpt4 explanation huggingface data-science neuroscience ai-for-science language-model interpretability machine-learning fmri-data-analysis large-language-models artificial-intelligence interpretable-embeddings automated-interpretability natural-language-processing mechanistic-interpretability
Created 2023-01-30
418 commits to main branch, last one 14 days ago
aryamanarora
causalgym aryamanarora
6
41
unknown
1
CausalGym: Benchmarking causal interpretability methods on linguistic tasks
benchmark causality syntaxgym interpretability mechanistic-interpretability
Created 2023-10-10
309 commits to main branch, last one 4 months ago
wesg52
universal-neurons wesg52
6
27
mit
3
Universal Neurons in GPT2 Language Models
llm ai-safety interpretability mechanistic-interpretability
Created 2023-12-26
5 commits to main branch, last one 10 months ago
yash-srivastava19
arrakis yash-srivastava19
1
26
unknown
1
Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.
garcon anthropic transformer explainable-ai transformerlens mechanistic-interpretability
Created 2024-07-10
11 commits to main branch, last one 8 months ago
Nix07
finetuning Nix07
4
25
unknown
1
This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking".
finetuning entity-tracking science-of-deep-learning mechanistic-interpretability
Created 2023-08-16
272 commits to main branch, last one about a year ago