method
active
method:umap-visualization-for-featuresUMAP visualization for features
Dimensionality reduction of SAE decoder vectors to create interactive feature maps.
Neighborhood — ranked by edge-count
Methods (1)
method
- UMAP Embedding of Featuresrelated_to2D embedding of feature direction vectors used to visualize feature clusters and splitting geometry
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.
- Method of optimizing input to cause a neuron to fire maximally, used to characterize what a neuron detects; establishes causal link
- Used to visualize LLM true/false representations, revealing clear linear structure separating true from false statements
- Used to visually inspect separation of truth-related directions in model activation space across layers
- Metaphor treating each system feature or function as a separate application that can be independently loaded and managed.
- The central object of study — the idea that a concept like truth is encoded as a direction in the LLM's latent space
- Feature that activates across all tokens within a specific context (e.g., DNA sequences, base64 strings)
- Dual interpretation of features: in addition to responding to inputs, features also act to increase probability of specific output tokens
- A feature that responds to only a single latent variable, contrasted with polysemantic features