11 dependents
Package Description Downloads/month
Library for extracting and analyzing persona vectors 4K
Unified access to Large Language Model modules using NNsight 3K
🪄 Interpreto is an interpretability toolbox for LLMs 2K
Dictionary learning via sparse autoencoders on neural network activations 1K
Cross-Layer Transcoder Library 488
open source mech interp circuit tracing library 451
Neural Network Easy Extraction - Simple LLM activation extraction in one line 185
Making Transformers Obvious 176
162
The NDIF server, which performs deep inference and serves nnsight requests remot... 74
Mech. Interp. utility kit 21