Project Presentations: Interpretability Hackathon 2.0

Check out the presentations from some of the projects submitted during the Interpretability 2.0 Apart Hackathon, hosted by Apart Research [https://apartresearch.com/] in April of 2023.

Join future hackathons at https://apartresearch.com/sprints/. Our moderator and organizer is Esben Kran and Apart Research.

Read Neel Nanda's quickstart guide here: https://alignmentjam.com/post/quickstart-guide-for-mechanistic-interpretability/
Check out more ideas here: https://aisi.ai/list/interpretability-hackathon/
See a collection of tutorials and starter code here: https://alignmentjam.com/interpretability/

This video is a slightly trimmed-down version of the livestream found at https://youtube.com/live/DZCxnkTTw7E.

Видео Project Presentations: Interpretability Hackathon 2.0 канала Apart - Safe AI