Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering 事件

Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering arXiv:2506.01247v3 Announce Type: replace Abstract: Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. We study whether sparse visual features can be used not only for post-hoc analysis, but also to steer frozen vision-language models. We introduce Visual Sparse Steering (