Monosemantic Functional Features

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

• monosemanticityconcept0.844
  Interpretability property where a latent feature represents a single semantic concept; benchmarked across architectures.
• Monosemanticity and entanglement of SAE features were benchmarked for clinical taxonomy grounding across SleepFM, REVE, LaBraM.finding0.792
  Quantitative assessment of feature quality using clinical concepts across models.
• Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet (Templeton et al., 2024)concept0.752
  Key paper on scaling SAE-based interpretability to frontier models, cited as precedent
• Polysemanticityconcept0.746
  Neurons that respond to multiple unrelated concepts, limiting interpretability.
• Towards Monosemanticity: Decomposing Language Models with Dictionary Learning (Bricken et al., 2023)concept0.743
  Foundational SAE mechanistic interpretability paper
• Superposition of Sparse Featuresconcept0.742
  Mechanistic finding by Bricken et al. 2023 about how LLMs store features; cited as operational justification for pattern-repository assumption
• SAE features can be grounded in clinical taxonomy (abnormality, age, sex, medication) to benchmark monosemanticity and entanglement.claim0.741
  Claim that feature grounding enables interpretability metrics.
• Feature Sparsityconcept0.730
  Property that features activate on only a small fraction of inputs; enables compressed sensing and is what allows superposition to work