Popular repositories Loading

1. TransformerLens TransformerLens Public

   Forked from TransformerLensOrg/TransformerLens

   A library for mechanistic interpretability of GPT-style language models

   Python

2. SAELens SAELens Public

   Forked from jbloomAus/SAELens

   Training Sparse Autoencoders on Language Models

   Jupyter Notebook

3. numpy-100 numpy-100 Public

   Forked from rougier/numpy-100

   100 numpy exercises (with solutions)

   Python

4. delphi delphi Public

   Forked from EleutherAI/delphi

   Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models know themselves through automated interpretability.

   Python

5. sparsify sparsify Public

   Forked from EleutherAI/sparsify

   Sparsify transformers with SAEs and transcoders

   Python