method
active
method:iterative-codebook-feature-learningIterative Codebook Feature Learning
Flexible decoding technique mentioned as possible remedy.
Neighborhood — ranked by edge-count
Papers (1)
paper
Hypotheses (1)
hypothesis
- Proposed remedy.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Candidate approach to solving superposition.
- Learning through Bayesian model averaging over policies, leading to habitual behavior.
- Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.
- Repetitive behavioral pattern observed under high steering strengths in SAE feature self-steering experiments
- The ability of active inference agents to learn their own prior preferences over outcomes by accumulating Dirichlet parameters from experience.
- AI training method inspired by behaviorism, used for autonomous cars and drones; cited as bioinspired success
- Motivation for using sparsity-based dictionary learning on language models
- Method of optimizing input to cause a neuron to fire maximally, used to characterize what a neuron detects; establishes causal link