facebookresearch/llm-transparency-tool

A library for mechanistic interpretability of GPT-style language models

Unified access to Large Language Model modules using NNsight

To know what models don't say out loud.

Companion code for the global workspace interpretability paper

🪄 Interpreto is an interpretability toolbox for LLMs

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

In-Context Explainability 360 toolkit

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.