GeezerVison

confirmlabs.org

Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).

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.

repository for sharing / working on code with collaborators

The Imprint Project

Fluent student-teacher redteaming