
38.3 - Erik Jenner on Learned Look-Ahead
AXRP - the AI X-risk Research Podcast
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.