EleutherAI/sparsify

Training Sparse Autoencoders on Language Models

A library for mechanistic interpretability of GPT-style language models

A framework for training, analyzing, and visualizing sparse autoencoders and related interpretability methods

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Prune transformer layers

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.

Implementation for MatMul-free LM.

Unified access to Large Language Model modules using NNsight

Utils for Unsloth https://github.com/unslothai/unsloth