
AXRP - the AI X-risk Research Podcast
38.2 - Jesse Hoogland on Singular Learning Theory
Mittwoch, 27. November 2024 · 18 min
Kapitelklicken springt direkt hin
Shownotes
You may have heard of singular learning theory, and its "local learning coefficient", or LLC - but have you heard of the refined LLC? In this episode, I chat with Jesse Hoogland about his work on SLT, and using the refined LLC to find a new circuit in language models.
Patreon: patreon.com/axrpodcast
Ko-fi: ko-fi.com/axrpodcast
The transcript: axrp.net/episode/2024/11/27/38_2-jesse-hooglan…
FAR.AI: far.ai
FAR.AI on X (aka Twitter): x.com/farairesearch
FAR.AI on YouTube: youtube.com/@FARAIResearch
The Alignment Workshop: alignment-workshop.com
Topics we discuss, and timestamps:
- About Jesse
- The Alignment Workshop
- About Timaeus
- SLT that isn't developmental interpretability
- The refined local learning coefficient
- Finding the multigram circuit
Links:
Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient: arxiv.org/abs/2410.02984
Investigating the learning coefficient of modular addition: hackathon project: lesswrong.com/posts/4v3hMuKfsGatLXPgt/investig…
Episode art by Hamish Doodles: hamishdoodles.com