🧑‍🔬 Atticus Geiger

🏛️ Affiliations

🔬Harvard University PressCambridge · United States2026 · 1 papercurrent🎓Stanford UniversityStanford · United States2019–2024 · 17 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 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.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation (2020 · 112 citations)
   The question is whether neural NLI models learn how negation reverses lexical entailment: "dance" entails "move", but "not move" does not entail "not dance".
2. Interpretability at Scale: Identifying Causal Mechanisms in Alpaca (2023 · 70 citations)
   Causal-abstraction methods test whether a neural network actually implements a human-readable algorithm, but until now they had only been applied to small, task-specific models.
3. Posing Fair Generalization Tasks for Natural Language Inference (2019 · 58 citations)
   Adversarial and synthetic test sets often show that NLI models with strong scores on naturalistic corpora break down on systematic cases.

All works

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

1. Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and NegationAtticus Geiger, Kyle Richardson, Christopher PottsEnglish · 112 citations
2. Interpretability at Scale: Identifying Causal Mechanisms in AlpacaConference on Neural Information Processing Systems (NeurIPS)Zhengxuan Wu, Atticus Geiger, Thomas Icard, et al.2023 · 70 citations
3. ReFT: Representation Finetuning for Language ModelsarXiv:2404.03592 · original ↗ · no summary yetZhengxuan Wu et al.2024 · 66 citations
4. Finding Alignments Between Interpretable Causal Variables and Distributed Neural RepresentationsarXiv:2303.02536 · original ↗ · no summary yetAtticus Geiger et al.2023 · 66 citations
5. Linear Representations of Sentiment in Large Language ModelsarXiv:2310.15154 · original ↗ · no summary yetCurt Tigges et al.2023 · 62 citations
6. Posing Fair Generalization Tasks for Natural Language InferenceConference on Empirical Methods in Natural Language Processing (EMNLP)Atticus Geiger, Ignacio Cases, Lauri Karttunen, et al.2019 · 58 citations
7. AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse AutoencodersarXiv:2501.17148 · original ↗ · no summary yetZhengxuan Wu et al.2025 · 51 citations
8. Rigorously Assessing Natural Language Explanations of NeuronsProceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP · original ↗ · no summary yetJing Huang et al.2023 · 26 citations
9. Enhancing Automated Interpretability with Output-Centric Feature DescriptionsProceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · original ↗ · no summary yetYoav Gur-Arieh et al.2025 · 13 citations
10. Constructing Interpretable Features from Compositional Neuron GroupsProceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · original ↗ · no summary yetOr David Shafran, Atticus Geiger, Mor Geva2026 · 1 citation

🤝 Co-authors here

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

• Christopher Potts ×3
• Ignacio Cases
• Kyle Richardson
• Lauri Karttunen
• Noah D. Goodman

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) ×2
• BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP: BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2020
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2019
• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2023
• Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP

🔗 Cited by

Papers of our library cite their works 400 times (of the 141,840 papers whose bibliographies we read); 16 citing papers with a page here →.

Updated 24 October 2026

↑ back to top

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