Elamur Research⌕
☰
home / authors / Wes Gurnee

Wes Gurnee

Wes Gurnee has 2 papers in our library, in 2023–2024, most of them on Language models & pretraining, Interpretability, Bias, fairness & safety; often with Neel Nanda, Aaquib Syed, Daniel Paleka.

2 papers in our library · 2023–2024

OpenAlex · ORCID · h-index 6 · 21 works · 213 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 303 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #5398

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Massachusetts Institute of TechnologyCambridge · United States2021–2026 · 10 papersEducation since 2021 · PhD, Operations Research Centercurrent🏢AnthropicSan Francisco · United States2026 · 1 papercurrent🎓Cornell UniversityIthaca · United States2016–2020Education 2016–2020 · Bachelor of Science, Computer Science

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 work

🧭 Topics 3Research subjects and languages the work is about.Interpretability · 1 workBias, fairness & safety · 1 workLanguage models & pretraining · 1 work

 Works by year

2020s

20241 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Refusal in Language Models Is Mediated by a Single Direction (2024 · 196 citations)
    Chat LLMs are safety-tuned to decline harmful requests, but how this behavior works inside the model is poorly understood.
  2. Finding Neurons in a Haystack: Case Studies with Sparse Probing (2023 · 123 citations)
    Large language models are hard to inspect. It is unclear how text properties that humans can recognize are stored in individual MLP neurons, especially when a network must encode more features than it has neurons (superposition). The authors introduce sparse probing: linear classifiers that may use at most k neurons…

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. Refusal in Language Models Is Mediated by a Single DirectionarXiv:2406.11717Andy Arditi, Oscar Obeso, Aaquib Syed, et al.2024 · 196 citations
  2. Finding Neurons in a Haystack: Case Studies with Sparse ProbingarXiv:2305.01610Wes Gurnee, Neel Nanda, Matthew Pauly, et al.2023 · 123 citations
  3. Training Dynamics of Contextual N-Grams in Language Models ↗arXiv:2311.00863 · no summary yetLucia Quirke et al.2023 · 5 citations

 Co-authors here

4 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 303 times (of the 149,439 papers whose bibliographies we read); 77 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/wes-gurnee/