Where Grokking Happens: Distributed Utility and Fourier Recoding Without a Module Switch
arXiv:2609.17571v1 Announce Type: cross Abstract: Where in a Transformer is the change from memorization to generalization functionally expressed? We introduce Transition Games--behavior-aligned exact activation games with paired non-generalizing controls--and
arXiv cs.AI··Updated just now·34 sightings