mechanistic-interpretability topic

Explain a black-box module in natural language.

microsoft

Sparse and discrete interpretability tool for neural networks

taufeeque9

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

stanfordnlp

🧠 Starter templates for doing interpretability research

apartresearch

Sparse probing paper full code.

wesg52

Universal Neurons in GPT2 Language Models

wesg52

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...

pauljblazek

Steering vectors for transformer language models in Pytorch / Huggingface

steering-vectors

CausalGym: Benchmarking causal interpretability methods on linguistic tasks

aryamanarora

Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".

epfl-dlab