method
active
method:feature-visualizationFeature Visualization
Method of optimizing input to cause a neuron to fire maximally, used to characterize what a neuron detects; establishes causal link
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Dimensionality reduction of SAE decoder vectors to create interactive feature maps.
- Used to visualize LLM true/false representations, revealing clear linear structure separating true from false statements
- Used to visually inspect separation of truth-related directions in model activation space across layers
- Technique of building a fluid, three-dimensional vision by closing one's eyes, relying on words and feeling to avoid arbitrary graphical over-specification.
- Property that features activate on only a small fraction of inputs; enables compressed sensing and is what allows superposition to work
- Domain of techniques for constructing informative features from raw data; covariance pooling is a feature engineering method for token sequences.
- Metaphor treating each system feature or function as a separate application that can be independently loaded and managed.
- Visual reasoning tasks often interleaved with intermediate visual states; promising direction in the field.