目標編集：トークン単位SAEステアリングとπ0.5における深さ限界

原文アブストラクト

Sparse autoencoders (SAEs) have recovered interpretable, causally relevant features in robot foundation models (RFMs) such as $π_{0.5}$ (arXiv:2603.19183, arXiv:2603.19233). SAE features on individual instruction tokens are less interpretable than timestep-pooled ones (arXiv:2603.19183), and whether they can redirect a robot's goal remains untested. We show that replacing the SAE features of a single goal word with those of an alternative goal word, leaving the instruction text unchanged, steers $π_{0.5}$-LIBERO into completing the alternative task. At layer 0, BatchTopK feature swaps redirect behavior in up to 20/20 rollouts in a scene where random-feature swaps redirect none, with success varying across six scenes in two LIBERO suites and across layers. The effect depends on SAE architecture: word-selected Matryoshka edits largely do not outperform random ones. SAEs are also not required. Adding a fixed difference-in-means vector at twice its natural magnitude redirects 8-10/10 rollouts. Layer-wise activation patching shows that goal-word edits remain effective up to layer 6 for object location and layer 2 for object identity, and up to layer 13 in both cases when patching also covers camera tokens. These results are proof of existence in an RFM in simulation and an initial map of how deep goal-redirecting edits remain effective. Visit https://doubleblind-sae-pi05.github.io for video rollouts.