Dynamically Scaled Activation Steering

Introduced Dynamically Scaled Activation Steering (DSAS), a method-agnostic framework that decouples when to steer from how to steer. DSAS adaptively modulates the strength of existing steering transformations across layers and inputs, intervening strongly only when undesired behavior is detected. At generation time, DSAS computes context-dependent scaling factors that selectively adjust the strength of any steering method. Demonstrated DSAS's generality by applying it to a text-to-image diffusion model, showing how adaptive steering allows the modulation of specific concepts. DSAS introduces minimal computational overhead while improving interpretability, pinpointing which tokens require steering and by how much.