The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Multimodal Neurons in Artificial Neural Networks
Open accessOverview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Many models form at least some interpretable features.
“Many models form at least some interpretable features.”
From Toy Models of Superposition (2022) · cites this paper as [19]
The Author Contributions section reports the discovery of many multimodal neurons in CLIP and says that some neuron activations were interpretable. That supports the existence of interpretable features in the model studied, but our copy does not establish the claim across many models. (LLM, conf=0.83)
Experimental — accuracy not yet measuredThere is evidence of interpretable neurons in RNNs, convolutional neural networks, and in some limited cases, transformer language models.
“There is evidence of interpretable neurons in RNNs ( e.g. ), convolutional neural networks ( see generally e.g. ; individual neuron families ), and in some limited cases, transformer language models ( see detailed discussion in our previous paper ).”
From Toy Models of Superposition (2022) · cites this paper as [19]
The citation is attached to the clause about interpretable neurons in transformer language models. The available passages from the Author Contributions section describe multimodal neurons in CLIP, while searches for “transformer language models,” “transformer,” and “language models” found no passage addressing interpretable neurons in transformer language models. The RNN and CNN examples have separate citations in the printed sentence. (LLM, conf=0.73)
Experimental — accuracy not yet measured
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Studies of interference in serial verbal reactions
Stroop, J. R. (1935) · Journal of Experimental Psychology · doi:10.1037/h0054651 · Cited by 18,622
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
Self-citationA Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
Invariant visual representation by single neurons in the human brain
Quiroga, R. Q., Reddy, L., Kreiman, G., Koch, C., & Fried, I. (2005) · Nature · doi:10.1038/nature03687 · Cited by 1,988
Separating Style and Content with Bilinear Models
Tenenbaum, J. B., & Freeman, W. T. (2000) · Neural Computation · doi:10.1162/089976600300015349 · Cited by 840
Concept cells: the building blocks of declarative memory functions
Quiroga, R. Q. (2012) · Nature reviews. Neuroscience · doi:10.1038/nrn3251 · Cited by 472
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
Self-citationLinear Algebraic Structure of Word Senses, with Applications to Polysemy
Arora, S., Li, Y., Liang, Y., Ma, T., & Risteski, A. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00034 · Cited by 186
Flagged first, then by citations
Cited by
Sorted by citations
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Hierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511
“Figure 5: Variations of images featuring typographic attacks [20] paired with the CLIP model’s predicted probabilities across three labels.”
BackgroundMethodInfluentialIn-context Learning and Induction Heads
Olsson, C., Elhage, N., Nanda, N., Joseph, N., DasSarma, N., Henighan, T., Mann, B., Askell, A., Bai, Y., Chen, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2209.11895 · Cited by 1,170
Self-citationChatting about ChatGPT: how may AI and GPT impact academia and libraries?
Lund, B. D., & Wang, T. (2023) · Library Hi Tech News · doi:10.1108/lhtn-01-2023-0009 · Cited by 1,355
Lund, B. D., Wang, T., Mannuru, N. R., Nie, B., Shimray, S., & Wang, Z. (2023) · Journal of the Association for Information Science and Technology · doi:10.1002/asi.24750 · Cited by 919
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
Jeong, J., Zou, Y., Kim, T., Zhang, D., Ravichandran, A., & Dabeer, O. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01878 · Cited by 585
Artificial intelligence in histopathology: enhancing cancer research and clinical oncology
Shmatko, A., Ghaffari Laleh, N., Gerstung, M., & Kather, J. N. (2022) · Nature Cancer · doi:10.1038/s43018-022-00436-4 · Cited by 446
Red Teaming Language Models with Language Models
Perez, E., Huang, S., Song, F., Cai, T., Ring, R., Aslanides, J., Glaese, A., McAleese, N., & Irving, G. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.225 · Cited by 363
CLIPort: What and Where Pathways for Robotic Manipulation
Shridhar, M., Manuelli, L., & Fox, D. (2021) · arXiv · doi:10.48550/arxiv.2109.12098 · Cited by 223
CLIPasso: semantically-aware object sketching
Vinker, Y., Pajouheshgar, E., Bo, J. Y., Bachmann, R. C., Bermano, A. H., Cohen-Or, D., Zamir, A., & Shamir, A. (2022) · ACM Transactions on Graphics · doi:10.1145/3528223.3530068 · Cited by 217
From attribution maps to human-understandable explanations through Concept Relevance Propagation
Achtibat, R., Dreyer, M., Eisenbraun, I., Bosse, S., Wiegand, T., Samek, W., & Lapuschkin, S. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00711-8 · Cited by 181
Multimodal datasets: misogyny, pornography, and malignant stereotypes
Birhane, A., Prabhu, V. U., & Kahembwe, E. (2021) · arXiv · doi:10.48550/arxiv.2110.01963 · Cited by 160
Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks
Räuker, T., Ho, A., Casper, S., & Hadfield-Menell, D. (2023) · 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml54575.2023.00039 · Cited by 122
Elhage, N., Hume, T., Olsson, C., Schiefer, N., Henighan, T., Kravec, S., Hatfield-Dodds, Z., Lasenby, R., Drain, D., Chen, C., et al. (2022) · arXiv · doi:10.48550/arxiv.2209.10652 · Cited by 51
Self-citationLanguage Models Represent Space and Time
Gurnee, W., & Tegmark, M. (2023) · arXiv · doi:10.48550/arxiv.2310.02207 · Cited by 46
Wolfe, R., Yang, Y., Howe, B., & Caliskan, A. (2023) · 2023 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3593013.3594072 · Cited by 42
Emergent Linear Representations in World Models of Self-Supervised Sequence Models
Nanda, N., Lee, A., & Wattenberg, M. (2023) · Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/2023.blackboxnlp-1.2 · Cited by 55
Human Beauty according to Artificial Intelligence
Kenig, N., Monton Echeverria, J., & Muntaner Vives, A. (2023) · Plastic and Reconstructive Surgery - Global Open · doi:10.1097/gox.0000000000005153 · Cited by 30
Marks, S., & Tegmark, M. (2023) · arXiv · doi:10.48550/arxiv.2310.06824 · Cited by 21
Evidence for Hypodescent in Visual Semantic AI
Wolfe, R., Banaji, M. R., & Caliskan, A. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533185 · Cited by 19
Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
Geiger, A., Ibeling, D., Zur, A., Chaudhary, M., Chauhan, S., Huang, J., Arora, A., Wu, Z., Goodman, N., Potts, C., et al. (2023) · arXiv · doi:10.48550/arxiv.2301.04709 · Cited by 11
Universality of representation in biological and artificial neural networks
Hosseini, E., Casto, C., Zaslavsky, N., Conwell, C., Richardson, M., & Fedorenko, E. (2024) · doi:10.1101/2024.12.26.629294 · Cited by 10
Metadata
- Authors
- Goh, G., Cammarata, N., Voss, C., Carter, S., Petrov, M., Schubert, L., Radford, A., & Olah, C.
- Affiliations
- OpenAI (United States) (US)
- Observable
- None
- Venue
- Distill
- Publisher
- Distill Working Group
- Published
- 2021-03-04
- Volume
- 6
- Issue
- 3
- ISSN
- 2476-0757 (ISSN-L)
- OpenAlex
- W3134095442
- Cited by
- 330
- References
- 11
- Citations by year
- 2026: 53 · 2025: 46 · 2024: 73 · 2023: 57 · 2022: 73 · 2021: 27
- FWCI
- 16.79
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by
- Locations
- Distill (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- artificial neural networks, multimodal learning
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
