On Interpretability and Feature Representations: An Analysis of the Sentiment Neuron
The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The first issue is that the method relies on human prior beliefs, which may lead interpreters to project their human understanding onto models that may, in fact, be using unfamiliar concepts.”
From Open Problems in Mechanistic Interpretability (2025) · cites this paper as Donnelly & Roegiest, 2019
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Object Detectors Emerge in Deep Scene CNNs
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2014) · arXiv · doi:10.48550/arxiv.1412.6856 · Cited by 971
Visualizing and Understanding Recurrent Networks
Karpathy, A., Johnson, J., & Fei-Fei, L. (2015) · arXiv · doi:10.48550/arxiv.1506.02078 · Cited by 845 · cited 1×
“Several authors [13, 2, 9] have investigated the idea that single neurons or groups of neurons have easily interpretable behaviour.”
BackgroundLearning to Generate Reviews and Discovering Sentiment
Radford, A., Jozefowicz, R., & Sutskever, I. (2017) · arXiv · doi:10.48550/arxiv.1704.01444 · Cited by 330 · cited 6×
“This leads us to conclude that, contrary to Radford et al. [9], there is a meaningful amount of sentiment information stored outside of the SN.”
BackgroundMethodResultInfluentialOn the importance of single directions for generalization
Morcos, A. S., Barrett, D. G. T., Rabinowitz, N. C., & Botvinick, M. (2018) · arXiv · doi:10.48550/arxiv.1803.06959 · Cited by 305
Research works printed but not linked: 7
- Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2018) · DOI · Paper page
- Krause, B., Lu, L., Murray, I., Renals, S.: Multiplicative LSTM for sequence modelling. In: International Conference on Learning Representations (2017)
- Maas, A.L., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1, HLT 2011, pp. 142–150. Association for Computational Linguistics, Stroudsburg (2011)
- Pang, B., Lee, L.: Seeing stars: exploiting class relationships for sentiment categorization with respect to rating scales. In: Proceedings of ACL, pp. 115–124 (2005) · DOI · Paper page
- Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1631–1642. Association for Computational Linguistics, Seattle, Washington, October 2013
- Wang, S., Manning, C.D.: Baselines and bigrams: simple, good sentiment and topic classification. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers - Volume 2, ACL 2012, pp. 90–94 (2012)
- Wiebe, J., Wilson, T., Cardie, C.: Annotating expressions of opinions and emotionsin language. Lang. Resour. Eval. 1 (2005) · DOI · Paper page
Cited by
Sentiment analysis using deep learning architectures: a review
Yadav, A., & Vishwakarma, D. K. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-019-09794-5 · Cited by 841
Open Problems in Mechanistic Interpretability
Sharkey, L., Chughtai, B., Batson, J., Lindsey, J., Wu, J., Bushnaq, L., Goldowsky-Dill, N., Heimersheim, S., Ortega, A., Bloom, J., et al. (2025) · arXiv · doi:10.48550/arxiv.2501.16496 · Cited by 291
Zoom In: An Introduction to Circuits
Olah, C., Cammarata, N., Schubert, L., Goh, G., Petrov, M., & Carter, S. (2020) · Distill · doi:10.23915/distill.00024.001 · Cited by 288
Cammarata, N., Goh, G., Carter, S., Schubert, L., Petrov, M., & Olah, C. (2020) · Distill · doi:10.23915/distill.00024.003 · Cited by 41
Finding Neurons in a Haystack: Case Studies with Sparse Probing
Gurnee, W., Nanda, N., Pauly, M., Harvey, K., Troitskii, D., & Bertsimas, D. (2023) · arXiv · doi:10.48550/arxiv.2305.01610 · Cited by 15
“While probing in general has a number of limitations [14, 28, 15, 29, 30], our work seeks to address, at least partially, the shortcomings most associated with probing individual neurons [13].”
BackgroundInfluential
Metadata
- Authors
- Donnelly, J., & Roegiest, A.
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2019
- Pages
- 795-802
- ISSN
- 0302-9743
- 1611-3349
- Cited by
- 10
- References
- 4
- Language
- en
- Licence
- www.springer.com/tdm (tdm)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: On Interpretability and Feature Representations: An Analysis of the Sentiment Neuron. https://app.cochat.ai/papers/10.1007/978-3-030-15712-8_55
- The paper
- Donnelly, J., & Roegiest, A. (2019). On Interpretability and Feature Representations: An Analysis of the Sentiment Neuron. Lecture Notes in Computer Science. https://doi.org/10.1007/978-3-030-15712-8_55
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.