Pure Feature

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

• Pure Functional Programmingframework0.787
  A paradigm relying on recursion equations without assignment; Linda authors compare it on DNA sequence similarity problem.
• Pure unityconcept0.783
  The ultimate condition of living structure where the whole becomes a single, undivided entity made of beings, all rooted in the same I.
• Feature Sparsityconcept0.774
  Property that features activate on only a small fraction of inputs; enables compressed sensing and is what allows superposition to work
• feature as applicationconcept0.759
  Metaphor treating each system feature or function as a separate application that can be independently loaded and managed.
• Feature Visualizationmethod0.758
  Method of optimizing input to cause a neuron to fire maximally, used to characterize what a neuron detects; establishes causal link
• Action Featuresconcept0.757
  Dual interpretation of features: in addition to responding to inputs, features also act to increase probability of specific output tokens
• Feature Universalityconcept0.753
  Property of features that form consistently across different models trained on the same or similar data, suggesting features are real representational units
• Sparse Feature Dictionaryconcept0.751
  The extracted set of sparse interpretable features from model embeddings via SAEs