AI RESEARCH
Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry
arXiv CS.AI
•
ArXi:2510.08638v3 Announce Type: replace-cross DINOv2 is routinely deployed to recognize objects, scenes, and actions; yet the nature of what it perceives remains unknown. As a working baseline, we adopt the Linear Representation Hypothesis (LRH) and operationalize it using SAEs, producing a 32,000-unit dictionary that serves as the interpretability backbone of our study, which unfolds in three parts.