finding
active
finding:inceptionv1-neuron-4e-55-responds-to-cat-faces-fronts-of-cars-and-cat-legs-as-unrelated-stimuliInceptionV1 neuron 4e:55 responds to cat faces, fronts of cars, and cat legs as unrelated stimuli
Concrete example of polysemantic neuron demonstrating the challenge to the circuits agenda
Source paper
extracted_from(2020) · Chris Olah · Nick Cammarata · Ludwig Schubert · Gabriel Goh +2
Neighborhood — ranked by edge-count
Concepts (1)
concept
- Polysemantic NeuronsupportsA neuron that responds to multiple unrelated inputs, posing a major challenge for circuit-level interpretation
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Evidence that neural networks learn sophisticated invariance mechanisms through structured circuits rather than loose feature aggregation
- Circuit-level evidence that polysemantic neurons arise deliberately through superposition rather than entangled computation
- Prior finding cited as convergent evidence for LLM self-awareness capacities
- Open question about inter-agent communication beyond model-space assumption
- Demonstrates that meaningful algorithms can be read directly off floating-point weights in a neural network
- Empirical basis for expanding sentience frameworks; shows Crump criteria adaptable beyond traditional neurocentric definitions.
- Fundamental assertion: single imperative (free energy minimization) explains diverse cognitive and neural phenomena.
- Generalization of the criteria beyond neurons.