Metonymic circuits reveal how Vision Transformers ground abstract concepts
This arXiv paper introduces the concept of "metonymic circuits": intermediate, concrete anchor concepts (e.g., fire) that bridge visual signals to abstract labels (e.g., angry) in Vision Transformers. Using Transcoders applied to CLIP and DINO encoders and a curated icon dataset, the authors trace structured circuits where perceptual primitives appear in early layers, object-like anchors precede abstract targets, images with rendered text use a distinct perceptual-to-textual route, and causal interventions indicate these intermediates are functionally involved in grounding abstract concepts.