atomic features

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

• Fourier featuresconcept0.743
  Features identified in Llama-3.1-8B that compute sums using periods respecting base-10 addition (2, 5, 10) rather than concept-specific periods
• Action Featuresconcept0.740
  Dual interpretation of features: in addition to responding to inputs, features also act to increase probability of specific output tokens
• feature as applicationconcept0.723
  Metaphor treating each system feature or function as a separate application that can be independently loaded and managed.
• Pure Featureconcept0.719
  A feature that responds to only a single latent variable, contrasted with polysemantic features
• Feature engineeringconcept0.717
  Domain of techniques for constructing informative features from raw data; covariance pooling is a feature engineering method for token sequences.
• Geometry of featuresconcept0.716
  Research thread within About Blank concerning the structure and relational properties of neural network feature representations; covariance pooling tangentially supports this thread.
• Internal Featuresconcept0.712
  Representations inside LLMs that can be intervened upon.
• Feature Visualizationmethod0.708
  Method of optimizing input to cause a neuron to fire maximally, used to characterize what a neuron detects; establishes causal link