Elamur Research⌕
☰
home / authors / Nova DasSarma

Nova DasSarma

Nova DasSarma has 2 papers in our library, in 2022, most of them on Language models & pretraining, Interpretability; often with Ben Mann, Dawn Drain, Nelson Elhage.

2 papers in our library · 2022

OpenAlex · h-index 13 · 14 works · 1,690 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 3,936 times in our library · 6 more in our library without a page yet · ⭐ Paper Stars ranking: #3593

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

🔬Open Philanthropy ProjectSan Francisco · United States2024 · 1 papercurrent🤝Machine Intelligence Research InstituteBerkeley · United States2022–2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

 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 2Research subjects and languages the work is about.Language models & pretraining · 1 workInterpretability · 1 work

💡 Concepts 2Key ideas and methods explained on our concept pages.Few-shot learning · 1 workScaling laws · 1 work

 Works by year

2020s

20222 papers

 Papers

The most cited first (OpenAlex and our library).

  1. In-context Learning and Induction Heads (2022 · 475 citations)
    The authors from Anthropic search for the internal mechanism of transformer language models that is responsible for in-context learning.
  2. Scaling Laws and Interpretability of Learning from Repeated Data (2022 · 91 citations)
    Large language models often see the same data several times. Sometimes this is done deliberately, to upweight high-quality sources, and sometimes it results from incomplete deduplication. The authors from Anthropic investigate why even a small fraction of repeated data harms models so severely. They train a family of…

All works

8 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. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback ↗arXiv:2204.05862 · no summary yetYuntao Bai et al.2022 · 1,778 citations
  2. Language Models (Mostly) Know What They Know ↗arXiv:2207.05221 · no summary yetSaurav Kadavath et al.2022 · 827 citations
  3. In-context Learning and Induction HeadsarXiv:2209.11895Catherine Olsson, Nelson Elhage, Neel Nanda, et al.2022 · 475 citations
  4. A General Language Assistant as a Laboratory for Alignment ↗arXiv:2112.00861 · no summary yetAmanda Askell et al.2021 · 432 citations
  5. Predictability and Surprise in Large Generative Models ↗arXiv:2202.07785 · no summary yetDeep Ganguli et al.2022 · 268 citations
  6. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training ↗arXiv:2401.05566 · no summary yetEvan Hubinger et al.2024 · 123 citations
  7. Scaling Laws and Interpretability of Learning from Repeated DataarXiv:2205.10487Danny Hernandez, Tom Brown, Tom Conerly, et al.2022 · 91 citations
  8. Specific versus General Principles for Constitutional AI ↗arXiv (Cornell University) · no summary yetSandipan Kundu et al.2023 · 28 citations

 Co-authors here

12 of 15 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 3,936 times (of the 149,439 papers whose bibliographies we read); 714 citing papers with a page here →.

Updated

↑ back to top

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