Record
- Authors
- McGrath, T.; Rahtz, M.; Kramár, J.; Mikulik, V.; Legg, S.
- Year
- 2023
- Title
- The Hydra Effect: Emergent Self-repair in Language Model Computations
- Published in
- arXiv
- Type
- Preprint
- DOI
- 10.48550/arxiv.2307.15771
- arXiv
- arXiv:2307.15771
- Our note
- none yet
- Verification
- verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4385473442 · DOI 10.48550/arxiv.2307.15771 · arXiv:2307.15771 - From the lookup
- doi (the pages' own wording is under "As cited" below)
- Id
mcgrath-2023-hydra-effect-emergent-self-repair-language
Cited on
- Tracing Attention Computation Through Feature Interactions read status: not stated
As cited
The pages cite this work in one form.
-
McGrath, T., Rahtz, M., Kramár, J., Mikulik, V., and Legg, S. (2023). The Hydra Effect: Emergent Self-repair in Language Model Computations. arXiv:2307.15771.
BibLaTeX
@misc{mcgrath-2023-hydra-effect-emergent-self-repair-language,
author = {McGrath, T. and Rahtz, M. and Kramár, J. and Mikulik, V. and Legg, S.},
title = {{The Hydra Effect: Emergent Self-repair in Language Model Computations}},
date = {2023},
doi = {10.48550/arxiv.2307.15771},
eprint = {2307.15771},
eprinttype = {arxiv}
}