Metraipolis › archive › dc_8feb488db00c
Editing the Goal: Per-Token SAE Steering and Its Depth Limits in $π_{0.5}$ — arXiv:2611.00602
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00602
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:21:54.507Z
- SHA-256 of the archived text
79fd93a6bd8e03c7e6a008a336e3c33ef8942a439142817790d1f2e96880e78b- Stable URL of this page
https://metraipolis.com/documento/dc_8feb488db00c
How to cite
Editing the Goal: Per-Token SAE Steering and Its Depth Limits in $π_{0.5}$ — arXiv:2611.00602 — arXiv (en), https://arxiv.org/abs/2611.00602 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8feb488db00c (Metraipolis archive dc_8feb488db00c, sha256 79fd93a6bd8e03c7e6a008a336e3c33ef8942a439142817790d1f2e96880e78b)
BibTeX
@misc{dc8feb488db00c,
title = {Editing the Goal: Per-Token SAE Steering and Its Depth Limits in $π_0.5$ — arXiv:2611.00602},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00602},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8feb488db00c; sha256 79fd93a6bd8e03c7e6a008a336e3c33ef8942a439142817790d1f2e96880e78b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00602. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Sparse autoencoders (SAEs) have recovered interpretable, causally relevant features in robot foundation models (RFMs) such as $\pi_{0.5}$ ( 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 $\pi_{0.5}$-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 this https URL for video rollouts.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00602 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:19:49.774Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).