--- title: "Rohin Shah — author profile and papers" description: "Rohin Shah, Google DeepMind: 2 papers on Elamur Research (2023–2024), h-index 9 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/rohin-shah/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/rohin-shah/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Rohin Shah # Rohin Shah Rohin Shah has 2 papers in our library, in 2023–2024, most of them on [Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/); often with [Janos Kramar](https://md.research.elamur.ai/free/en/authors/janos-kramar/), [Neel Nanda](https://md.research.elamur.ai/free/en/authors/neel-nanda/), [Tom Lieberum](https://md.research.elamur.ai/free/en/authors/tom-lieberum/). 2 papers in our library · 2023–2024 [OpenAlex](https://openalex.org/A5012971694) · [ORCID](https://orcid.org/0000-0002-0656-2800) · [**h-index 9**](https://openalex.org/authors/A5012971694) · [45 works](https://openalex.org/works?filter=author.id:A5012971694) · [329 citations](https://openalex.org/works?filter=author.id:A5012971694&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/rohin-shah/#papers) · [🔗 238 citations in our library](https://md.research.elamur.ai/free/en/authors/rohin-shah/cited-by/) · [3 more in our library without a page yet](#also) · [⭐ Paper Star rank #4181](https://md.research.elamur.ai/free/en/paper-stars/page/42/#star-4181) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Rohin+Shah) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Rohin+Shah) · [dblp](https://dblp.org/search?q=Rohin+Shah) · [ACL Anthology](https://aclanthology.org/search/?q=Rohin+Shah) ## Affiliations [🏢**Google DeepMind** London · United Kingdom 2023–2026 · 3 papers*current*](https://md.research.elamur.ai/free/en/companies/google-deepmind/) · [🎓**University of California, Berkeley** Berkeley · United States 2014–2022 · 14 papers](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed. ## Concepts, shelves and topics Of its works in our library: the number of works on each and its rating among them. 💡 Concepts 2[Scaling laws · 1 work](https://md.research.elamur.ai/free/en/concepts/scaling-laws/) · [Lexicography · 1 work](https://md.research.elamur.ai/free/en/concepts/lexicography/) 📚 Shelves 1[AI & machine learning · 2 works](https://md.research.elamur.ai/free/en/shelves/ai/) 🧭 Topics 1[Interpretability · 1 work](https://md.research.elamur.ai/free/en/topics/interpretability/) ## Works by year ### 2020s [**2024** 1 paper](https://md.research.elamur.ai/free/en/papers/rajamanoharan-2024-improving-dictionary-learning-gated-sparse/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/papers/lieberum-2023-circuit-analysis-interpretability-scale-evidence/) ## Papers The most cited first (OpenAlex and our library). 1. **[Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla](https://md.research.elamur.ai/free/en/papers/lieberum-2023-circuit-analysis-interpretability-scale-evidence/)** *(2023 · 51 citations)* Circuit analysis has mostly been demonstrated on small networks, such as two-layer attention-only transformers or the 117M GPT-2. 2. **[Improving Dictionary Learning with Gated Sparse Autoencoders](https://md.research.elamur.ai/free/en/papers/rajamanoharan-2024-improving-dictionary-learning-gated-sparse/)** *(2024 · 39 citations)* Sparse autoencoders (SAEs) are used to break language model activations into sparse combinations of interpretable directions. ## Also in our library 3 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 5 co-authors with a page, the most papers together first. - [Janos Kramar](https://md.research.elamur.ai/free/en/authors/janos-kramar/) ×2 - [Neel Nanda](https://md.research.elamur.ai/free/en/authors/neel-nanda/) ×2 - [Tom Lieberum](https://md.research.elamur.ai/free/en/authors/tom-lieberum/) ×2 - [Geoffrey Irving](https://md.research.elamur.ai/free/en/authors/geoffrey-irving/) - [Vladimir Mikulik](https://md.research.elamur.ai/free/en/authors/vladimir-mikulik/) ## Cited by Papers of our library cite their works 238 times (of the 140,884 papers whose bibliographies we read); [9 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/rohin-shah/cited-by/). Updated 23 October 2026