Practical AI Alignment and Interpretability Research Group — Interpretability Work

Visit Grantee Site

Table of Contents

Image courtesy of the Practical AI Alignment and Interpretability Research Group

Open Philanthropy recommended a grant of $737,000 over two years to the Practical AI Alignment and Interpretability Research Group to support work led by Atticus Geiger to conduct interpretability research, create open-source course materials on mechanistic interpretability, and run a mentorship program.

This falls within our focus area of potential risks from advanced artificial intelligence.