The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Curve Detectors
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?
Cammarata et al. (2020) validated their interpretation of a curve detector's function in a convolutional neural network by substituting its parts with simple handcrafted replacements.
“Cammarata et al. (2020)validated their interpretation of a curve detector's function in a convolutional neural network by substituting its parts with simple handcrafted replacements.”
From Open Problems in Mechanistic Interpretability (2025) · cites this paper as Cammarata et al., 2020
In its discussion of causality, *Curve Detectors* says feature visualization and attribution experiments support the interpretation that the neurons detect curves. It does not describe validating that interpretation by substituting the detector’s parts with handcrafted replacements; it says the algorithm was reimplemented by hand and points to the next article for that account. (LLM, conf=0.86)
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
Learning to Generate Reviews and Discovering Sentiment
Radford, A., Jozefowicz, R., & Sutskever, I. (2017) · arXiv · doi:10.48550/arxiv.1704.01444 · Cited by 330
Flagged first, then by citations
Research works printed but not linked: 30
- Zeiler, Visualizing and understanding convolutional networks, 10.1007/978-3-319-10590-1_53 · DOI · Paper page
- Tang, Complex pattern selectivity in macaque primary visual cortex revealed by large-scale two-photon imaging, Current Biology, 28
- Mikolov, Distributed representations of words and phrases and their compositionality
- Karpathy, Visualizing and understanding recurrent networks, arXiv preprint arXiv:1506.02078 · arXiv
- Zhou, Object detectors emerge in deep scene cnns, arXiv preprint arXiv:1412.6856 · arXiv
- Olah, Feature Visualization, Distill, 10.23915/distill.00007 · DOI · Paper page
- Bau, Network Dissection: Quantifying Interpretability of Deep Visual Representations, 10.1109/CVPR.2017.354 · DOI · Paper page
- Donnelly, On Interpretability and Feature Representations: An Analysis of the Sentiment Neuron, 10.1007/978-3-030-15712-8_55 · DOI
- Jo, Measuring the tendency of CNNs to Learn Surface Statistical Regularities, arXiv preprint arXiv:1711.11561 · arXiv
- Geirhos, ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness, arXiv preprint arXiv:1811.12231 · arXiv
- Brendel, Approximating cnns with bag-of-local-features models works surprisingly well on imagenet, arXiv preprint arXiv:1904.00760 · arXiv
- Ilyas, Adversarial examples are not bugs, they are features
- Morcos, On the importance of single directions for generalization, arXiv preprint arXiv:1803.06959 · arXiv
- Erhan, Visualizing higher-layer features of a deep network, University of Montreal, 1341
- Simonyan, Deep inside convolutional networks: Visualising image classification models and saliency maps, arXiv preprint arXiv:1312.6034 · arXiv
- Nguyen, Deep neural networks are easily fooled: High confidence predictions for unrecognizable images, 10.1109/cvpr.2015.7298640 · DOI · Paper page
- Mordvintsev, Inceptionism: Going deeper into neural networks, Google Research Blog
- Nguyen, Plug & play generative networks: Conditional iterative generation of images in latent space, arXiv preprint arXiv:1612.00005 · arXiv
- Sundararajan, Axiomatic attribution for deep networks, arXiv preprint arXiv:1703.01365 · arXiv
- Selvaraju, Grad-cam: Why did you say that? visual explanations from deep networks via gradient-based localization, arXiv preprint arXiv:1610.02391 · arXiv
- Kindermans, PatternNet and PatternLRP--Improving the interpretability of neural networks, arXiv preprint arXiv:1705.05598, 10.1007/978-3-319-10590-1_53 · DOI · Paper page
- Kindermans, The (Un)reliability of saliency methods, arXiv preprint arXiv:1711.00867 · arXiv
- Adebayo, Sanity checks for saliency maps
- Mordvintsev, Differentiable Image Parameterizations, Distill, 10.23915/distill.00012 · DOI
- Olah, An overview of early vision in inceptionv1, Distill, 5
- Pasupathy, Responses to contour features in macaque area V4, Journal of neurophysiology, 82
- Jiang, Discrete neural clusters encode orientation, curvature and corners in macaque V4, bioRxiv, 10.1101/808907 · DOI
- Nakano, Neural painters: A learned differentiable constraint for generating brushstroke paintings, arXiv preprint arXiv:1904.08410 · arXiv
- Olah, The Building Blocks of Interpretability, Distill, 10.23915/distill.00010 · DOI · Paper page
- Carter, Using Artificial Intelligence to Augment Human Intelligence, Distill, 10.23915/distill.00009 · DOI
Cited by
Sorted by citations
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
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
The Quantization Model of Neural Scaling
Michaud, E. J., Liu, Z., Girit, U., & Tegmark, M. (2023) · arXiv · doi:10.48550/arxiv.2303.13506 · Cited by 57
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-citation
Metadata
- Authors
- Cammarata, N., Goh, G., Carter, S., Schubert, L., Petrov, M., & Olah, C.
- Affiliations
- OpenAI (United States) (US)
- Venue
- Distill
- Publisher
- Distill Working Group
- Published
- 2020-06-17
- Volume
- 5
- Issue
- 6
- ISSN
- 2476-0757 (ISSN-L)
- OpenAlex
- W4241940531
- Cited by
- 41
- References
- 1
- Citations by year
- 2026: 2 · 2025: 9 · 2024: 13 · 2023: 7 · 2022: 3 · 2021: 5 · 2020: 2
- FWCI
- 1.43
- Type
- journal article
- Language
- it
- Open access
- diamond
- doi.org
- Licence
- cc-by
- Locations
- Distill (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Object Detection Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Processing and 3D Reconstruction
- Keywords
- curve detection
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
