AI RESEARCH
The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth
arXiv CS.AI
•
ArXi:2605.24856v1 Announce Type: cross Concept formation in transformer language models is depth-extended, not a single-layer event: concepts emerge gradually across a contiguous region of the residual stream. Mechanistic interpretability methods identify the single layer of peak class separation -- the "best layer" -- capturing a snapshot rather than the process itself. We