Pinned Loading

1. ndif-team/nnsight ndif-team/nnsight Public

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

   Python 764 65

2. saprmarks/dictionary_learning saprmarks/dictionary_learning Public

   Python 383 91

3. multilingual-features multilingual-features Public

   Code for the paper "Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages" (NAACL 2025)

   Python 16 4

4. backward-chaining-circuits backward-chaining-circuits Public

   Forked from abhay-sheshadri/backward-chaining-circuits

   Code for the paper "Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task" (ACL 2024)

   Jupyter Notebook 9

5. social-biases-in-vision-transformers social-biases-in-vision-transformers Public

   [ICCV 2023] Official PyTorch implementation of "A Multidimensional Analysis of Social Biases in Vision Transformers"

   Python 13