Toy transformers may represent belief-state geometry optimally but not minimally

·LessWrong··

Methods note: The code used for the experiments and related open-source repo were built with Claude. The experimental design and writeup is my own, with minimal editing and formatting amendments made with Claude. Thesis A toy transformer keeps provably predictively defunct belief state data in its residual stream. This information is shed only when there is a sufficient amount of imposed capacity pressure, in which case the oldest predictively defunct information is shed first. Results I conduct...

Read full article →

Related Articles

NASA’s Mars Sample Return mission is dead
Muhammad523 · Hacker News · 18h ago
AMD's random number generator can't generate a 0?
BruceEel · Hacker News · 5h ago
What happened to the Snowden archive
EXHades · Hacker News · 1d ago
Samsung is expected to more than double output of its HBM4 and HBM4E DRAM
giuliomagnifico · Hacker News · 1d ago
MiMo-v2.6-Pro: Intelligence, Performance and Price Analysis
theanonymousone · Hacker News · 10h ago