My Neel Nanda MATS 10.0 Application: Studying Feature Splitting in SAEs via Training Data Attribution

Neel Nanda's MATS 12.0 Applications are open, apply here ! I thought I'd share my successful application from December 2025, it includes the executive summary, main content and the logbook I kept throughout! Here is the original doc I submitted. Some broad learnings: I really overcomplicated this application! Taking gradients through SAEs and doing data attribution was far too complicated and I…

See it on lesswrong.com ↗