Functional Specialization and Self-Persistent Routing of Native Tokens in ViTs

Vision Transformers (ViTs) increasingly employ auxiliary tokens such as $\text{[CLS]}$ and register ($\text{[REG]}$) tokens, yet their computational roles remain poorly understood. We analyze register-token dynamics using dual-path activation patching and introduce two complementary measures: Self-Autonomy, capturing causal persistence of token states, and Patch Receptivity, capturing their recoverability from spatial patch information. Across four DINOv2 scales and nine controlled visual conditions, register streams progressively specialize with depth and exhibit a clear Autonomy-Receptivity duality: shallow states are strongly patch-driven, whereas deeper states become increasingly self-persistent. These specialization patterns remain consistent across visual conditions despite changes in routing strength. Test-time register early-exit interventions further show that shallow register states can exert substantial downstream influence despite low Self-Autonomy. Our results reveal register tokens as heterogeneous, depth-dependent information-routing streams whose functional roles emerge and specialize throughout the network.