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

Methods (1)

method

Artifacts (1)

artifact
  • HeadVis
    analogous_to
    Interactive tool for visualizing attention heads across the full data distribution; frontend open-sourced.

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.
  • Visualizes feature interference matrix.
  • Used to visualize LLM true/false representations, revealing clear linear structure separating true from false statements
  • Featuresconcept0.802
    Interpretable concept representations hypothesized as basic units of computation.
  • Used to visually inspect separation of truth-related directions in model activation space across layers
  • Synthesizing inputs maximizing component activation.
  • Technique of building a fluid, three-dimensional vision by closing one's eyes, relying on words and feeling to avoid arbitrary graphical over-specification.
  • Planning featureconcept0.786
    Features that activate before the action sequence they bring about, fulfilling functions of intention