Metraipolis › archive › dc_7cf5b8d5c49f
Rethinking Circuit Evaluation: Do Circuits Explain Model Errors? — arXiv:2609.35686
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35686
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:03:53.108Z
- SHA-256 of the archived text
60384aa895be2b8dd837dcf410228f0984672bfb0c76559ae2b3cc5aa642bd73- Stable URL of this page
https://metraipolis.com/documento/dc_7cf5b8d5c49f
How to cite
Rethinking Circuit Evaluation: Do Circuits Explain Model Errors? — arXiv:2609.35686 — arXiv (en), https://arxiv.org/abs/2609.35686 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cf5b8d5c49f (Metraipolis archive dc_7cf5b8d5c49f, sha256 60384aa895be2b8dd837dcf410228f0984672bfb0c76559ae2b3cc5aa642bd73)
BibTeX
@misc{dc7cf5b8d5c49f,
title = {Rethinking Circuit Evaluation: Do Circuits Explain Model Errors? — arXiv:2609.35686},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35686},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cf5b8d5c49f; sha256 60384aa895be2b8dd837dcf410228f0984672bfb0c76559ae2b3cc5aa642bd73},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35686. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Mechanistic interpretability (MI) aims to explain a model's behaviour through analyzing its internal computations; circuit-based explanations aim to isolate these computations with compact subnetworks validated by ablating the rest of the model. We show that circuits validated this way may fail to recover the underlying mechanism of the model's behaviour by closely reproducing its successful decisions while failing to account for most of its errors. Such explanations should account for the model's particular errors as well as its successes. We evaluate this requirement by measuring exact answer agreement separately on model successes and failures, across circuit sizes and ablation settings, on IOI, Docstring, and six model-task settings from the Mechanistic Interpretability Benchmark. We discover that many tested circuits closely replicate correct behaviour while missing most of the model's errors. On indirect object identification (IOI) for GPT-2 small, under mean ablation, the manual circuit and tested automated circuits, including one trained against the model's full output distribution, agree with the model on 97.3-99.5% of prompts it answers correctly but only 11.4-41.7% of errors. An IOI case study shows that lost errors are recoverable by restoring omitted attention-heads which raise error reproduction from 14.2% to 75.1% on a separate held-out set with 0.41 percentage point decrease on correct agreement, exceeding matched random extensions and scalar-biased control. Intervention traces show how omitted computations produce specific wrong answers for a reproducible subset of errors. In all, these findings show circuits can preserve task success without adequately explaining model's failures, and support exact error reproduction as a necessary, but not sufficient, test of circuit-based explanations of model behaviour. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.35686 — 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 2026-10-07T20:29:03.427Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).