geometry of activation space

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

• Direction (activation space)concept0.807
  A linear combination of neurons in a layer; the general form of a neural network feature including both individual neurons and other combinations
• Activation Manifoldconcept0.790
  The low-dimensional geometric structure discovered in neural activation space; contrasted with linear/Euclidean geometry.
• Sparse Activation Spacesconcept0.772
  Spaces of model activations from which sparse features are retrieved.
• Does the geometric structure of activation space causally shape neural network behavior?question0.756
  Central research question driving the work.
• Behavior Spaceconcept0.755
  A geometric space of all output token probability distributions, equipped with Hellinger distance, used to visualize model behavior.
• Emotion geometry in LLM activationsconcept0.743
  Emotion emerges early, peaks in middle layers, sharpens with scale, and persists across tokens in LLM activations per Zhang & Zhong 2025
• Configuration Spaceconcept0.743
  The ensemble of all possible configurations of a building, including incomplete states and paths between them.
• 3D behavioral spaceconcept0.739
  The traditional space of movement in the physical world where animals exhibit problem-solving behavior.