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 find distributed utility gain with a prospective block-0 attention bias; selected degree-two modes account for 67–92% of its addition contrast across replacement games, and a disjoint exact path study confirms that block-1 MLP mediates more of their effect than all other tested downstream paths in 12/12 pairs. The sharper "MLP memorizes, attention generalizes" prediction instead reverses (-.331 bits/example at the memory anchor; 0/12 in the predicted direction), while routing onset, global rank collapse, and a prime-invariant architecture ridge also fail, identifying grokking here as spectral recoding of an existing distributed circuit rather than a module switch.
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 find distributed utility gain with a prospective block-0 attention bias; selected degree-two modes account for 67–92% of its addition contrast across replacement games, and a disjoint exact path study confirms that block-1 MLP mediates more of their effect than all other tested downstream paths in 12/12 pairs. The sharper "MLP memorizes, attention generalizes" prediction instead reverses (-.331 bits/example at the memory anchor; 0/12 in the predicted direction), while routing onset, global rank collapse, and a prime-invariant architecture ridge also fail, identifying grokking here as spectral recoding of an existing distributed circuit rather than a module switch.
This article has been indexed from cs.AI updates on arXiv.org
Read the original article: