Metraipolis › archive › dc_744d25e2b247
The Linear Representation Hypothesis Needs a Group Action — arXiv:2609.27158
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27158
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T09:12:14.521Z
- SHA-256 of the archived text
77342ce4271fc35405c685ce5fc539f7529fe28519162966d165d3cfa6d0f3a4- Stable URL of this page
https://metraipolis.com/documento/dc_744d25e2b247
How to cite
The Linear Representation Hypothesis Needs a Group Action — arXiv:2609.27158 — arXiv (en), https://arxiv.org/abs/2609.27158 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_744d25e2b247 (Metraipolis archive dc_744d25e2b247, sha256 77342ce4271fc35405c685ce5fc539f7529fe28519162966d165d3cfa6d0f3a4)
BibTeX
@misc{dc744d25e2b247,
title = {The Linear Representation Hypothesis Needs a Group Action — arXiv:2609.27158},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27158},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_744d25e2b247; sha256 77342ce4271fc35405c685ce5fc539f7529fe28519162966d165d3cfa6d0f3a4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27158. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
To make claims about representations that generalize beyond a particular trained model, we need to specify when two representations should count as equivalent. The Linear Representation Hypothesis is often discussed without making this equivalence explicit. Different notions of equivalence preserve different structures, so metrics, probes, and interventions that appear to study the same representation may in fact correspond to different hypotheses. We therefore argue that the Linear Representation Hypothesis is not one hypothesis but a family of claims distinguished by representation equivalence. We formalize this idea using group actions, specifying the representation object, the procedure that produces it, and the property ultimately asserted, while accounting for equivalences imposed by the model architecture. This framework clarifies how assumptions can change across metrics, reading points, and analysis stages, and we use it to audit common representation quantities and recent interpretability analyses. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.27158 — 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 2026-10-08T08:13:26.625Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).