Elamur Research⌕
☰
home / authors / Thomas McGrath

Thomas McGrath

Thomas McGrath has 2 papers in our library, in 2023, most of them on Language models & pretraining; often with Arthur Conmy, Janos Kramar, Matthew Rahtz.

2 papers in our library · 2023

No OpenAlex profile matched yet.

📄 2 works in our library · 🔗 Cited 69 times in our library · ⭐ Paper Stars ranking: #9039

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

 Fields, topics and concepts

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

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 1 work

 Works by year

2020s

20232 papers

 Papers

The most cited first (OpenAlex and our library).

  1. The Hydra Effect: Emergent Self-repair in Language Model Computations (2023 · 49 citations)
    The paper asks how far ablation can be trusted for working out which parts of a large language model drive its predictions.
  2. Copy Suppression: Comprehensively Understanding an Attention Head (2023 · 25 citations)
    The paper addresses a long-standing difficulty in mechanistic interpretability. Explanations of model components usually hold only on narrow tasks, and "Negative Heads" that push against the right answer have puzzled earlier studies. The authors fully reverse-engineer one such head, L10H7 in GPT-2 Small, across its…

 Co-authors here

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

 Cited by

Papers of our library cite their works 69 times (of the 149,439 papers whose bibliographies we read); 19 citing papers with a page here →.

Updated

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