Curve Detector

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Symmetry detectorconcept0.801
  Functional role of SOHMs, detecting symmetries in input to compress information.
• Curve detectors found across AlexNet, InceptionV1, VGG19, ResNetV2-50 and models trained on Places365finding0.793
  Anecdotal evidence for the universality of low-level visual features across different architectures and datasets
• Curve detecting neurons found in every non-trivial vision model carefully examinedfinding0.740
  Empirical basis for treating curve detectors as a canonical example of meaningful, understandable features
• Diagnosismethod0.737
  The method of examining a neighborhood meter by meter to identify healthy and damaged places as the basis for ongoing repair.
• Weights between early and full curve detectors in InceptionV1 form a curve of positive weights at tangent positions, with opposing orientations inhibitoryfinding0.734
  Demonstrates that meaningful algorithms can be read directly off floating-point weights in a neural network
• thought detectionconcept0.730
  Task of detecting a model's internal thoughts; found by Lindsey (2026) to peak at ~2/3 depth in transformers.
• Binary Detection Taskmethod0.725
  Task paradigm from prior work asking 'Did you detect an injected thought?' via YES/NO logit comparison; shown here to be confounded
• Diagnostic Probingmethod0.715
  Earlier interpretability method applying classifiers to DNN hidden representations; shares complexity-accuracy dilemma with causal abstraction