ninjahawk/Subtext

Companion code for the global workspace interpretability paper

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo

A library for mechanistic interpretability of GPT-style language models

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.

🪄 Interpreto is an interpretability toolbox for LLMs

Keeping language models honest by directly eliciting knowledge encoded in their activations.

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

A curated list of Large Language Model (LLM) Interpretability resources.