🔗 Who cites «The Hydra Effect: Emergent Self-repair in Language Model Computations»

46 papers of our library cite it (of the 149,439 whose bibliographies we read) · 16 with a page here, the most cited first · ← back to «The Hydra Effect: Emergent Self-repair in Language Model Computations»

1. Explainability for Large Language Models: A SurveyACM Transactions on Intelligent Systems and TechnologyHaiyan Zhao, Hanjie Chen, Fan Yang, et al.2023 · 790 citations
2. Representation Engineering: A Top-Down Approach to AI TransparencyarXiv:2310.01405Andy Zou, Long Phan, Sarah Chen, et al.2023 · 397 citations
3. AI Alignment: A Comprehensive SurveyarXiv:2310.19852Jiaming Ji, Tianyi Qiu, Boyuan Chen, et al.2023 · 173 citations
4. Emergent Linear Representations in World Models of Self-Supervised Sequence ModelsarXiv:2309.00941Neel Nanda, Andrew Lee, Martin Wattenberg2023 · 116 citations
5. Mechanistic Interpretability for AI Safety — A ReviewarXiv:2404.14082Leonard Bereska, Efstratios Gavves2024 · 108 citations
6. Towards Best Practices of Activation Patching in Language Models: Metrics and MethodsarXiv:2309.16042Fred Zhang, Neel Nanda2023 · 97 citations
7. Foundational Challenges in Assuring Alignment and Safety of Large Language ModelsarXiv:2404.09932Usman Anwar, Abulhair Saparov, Javier Rando, et al.2024 · 87 citations
8. A Primer on the Inner Workings of Transformer-based Language ModelsarXiv:2405.00208Javier Ferrando, Gabriele Sarti, Arianna Bisazza, et al.2024 · 72 citations
9. Linear Representations of Sentiment in Large Language ModelsarXiv:2310.15154Curt Tigges, Oskar John Hollinsworth, Atticus Geiger, et al.2023 · 64 citations
10. Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop QueriesConference on Empirical Methods in Natural Language Processing (EMNLP)Eden Biran, Daniela Gottesman, Sohee Yang, et al.2024 · 55 citations
11. Information Flow Routes: Automatically Interpreting Language Models at ScaleConference on Empirical Methods in Natural Language Processing (EMNLP)Javier Ferrando, Elena Voita2024 · 43 citations
12. Successor Heads: Recurring, Interpretable Attention Heads In The WildarXiv:2312.09230Rhys Gould, Euan Ong, George Ogden, et al.2023 · 39 citations
13. AtP*: An efficient and scalable method for localizing LLM behaviour to componentsarXiv:2403.00745Janos Kramar, Tom Lieberum, Rohin Shah, et al.2024 · 32 citations
14. Copy Suppression: Comprehensively Understanding an Attention HeadarXiv:2310.04625Callum McDougall, Arthur Conmy, Cody Rushing, et al.2023 · 25 citations
15. Language Models Encode the Value of Numbers LinearlyInternational Conference on Computational Linguistics (COLING)Fangwei Zhu, Damai Dai, Zhifang Sui2025 · 15 citations
16. The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation AnalysisComputational LinguisticsAaron Mueller, Jannik Brinkmann, Millicent Li, et al.2026 · 7 citations

30 more papers of our library cite it; they have no page here yet.

This page in Markdown → https://md.research.elamur.ai/free/en/papers/mcgrath-2023-hydra-effect-emergent-self-repair/cited-by/