AXRP - the AI X-risk Research Podcast cover image

38.3 - Erik Jenner on Learned Look-Ahead

AXRP - the AI X-risk Research Podcast

CHAPTER

Exploring the Impact of Activation Patching on Model Performance

This chapter explores a complex activation patching experiment that blends data from corrupted and clean forward passes to assess the significance of information in various target squares. The findings highlight the critical impact of specific squares related to future moves on performance prediction, while also calling for deeper investigation into inconsistent experimental results.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner