Metonymic Circuits for Abstract Concept Grounding in Vision Transformers

תקציר מקורי באנגליתarXiv:2610.06928v1 Announce Type: new Abstract: We study how Vision Transformers ground abstract concepts (e.g., angry) when training data provide limited direct referential evidence. We hypothesize a metonymic grounding mechanism in which abstract predictions are driven by concrete, interpretable anchor concepts (e.g., fire) that bridge visual signals to abstract semantics. By applying Transcoders on CLIP and DINO vision encoders, we recover intermediate features that can be associated with semantic labels for more concrete concepts, and trace their contributions in circuits underlying abstract concept recognition. Experiments on a carefully curated icon dataset reveal structured metonymic circuits, in which perceptual primitives dominate early layers and object-like anchors precede abstr