Planning feature

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

• Feature Visualizationmethod0.786
  Method of optimizing input to cause a neuron to fire maximally, used to characterize what a neuron detects; establishes causal link
• feature as applicationconcept0.761
  Metaphor treating each system feature or function as a separate application that can be independently loaded and managed.
• Feature engineeringconcept0.756
  Domain of techniques for constructing informative features from raw data; covariance pooling is a feature engineering method for token sequences.
• Geometry of featuresconcept0.745
  Research thread within About Blank concerning the structure and relational properties of neural network feature representations; covariance pooling tangentially supports this thread.
• Feature (neural network)concept0.741
  Scalar function of the input corresponding to a direction in the vector space of neuron activations; claimed to be the fundamental unit of neural networks
• Feature Loopingconcept0.741
  Repetitive behavioral pattern observed under high steering strengths in SAE feature self-steering experiments
• Action Featuresconcept0.740
  Dual interpretation of features: in addition to responding to inputs, features also act to increase probability of specific output tokens
• Persona Featureconcept0.736
  An SAE latent representing a simulated character with consistent traits, as opposed to a specific trait