method
active
method:feature-visualization

Feature 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

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities 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.
  • Feature Sparsityconcept0.780
    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 reasoningconcept0.772
    Visual reasoning tasks often interleaved with intermediate visual states; promising direction in the field.