method
active
method:umap-embedding-of-featuresUMAP Embedding of Features
2D embedding of feature direction vectors used to visualize feature clusters and splitting geometry
Neighborhood — ranked by edge-count
Concepts (1)
concept
- Feature splittingsupportsPhenomenon where a feature in a small SAE splits into multiple finer features in a larger SAE.
Methods (1)
method
- UMAP visualization for featuresrelated_toDimensionality reduction of SAE decoder vectors to create interactive feature maps.
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.
- The specific type of representation studied in the paper: function f: X→R^n assigning feature vectors to inputs
- Extracting embeddings from instruction and example spans.
- A reinforcing interlock between different materials, mentioned alongside Deep Interlock in West Dean construction.
- Used to visualize embedding clusters in two dimensions for qualitative assessment of convergence
- Obtain instruction and example span embeddings at layer L* with chosen pooling.
- The component used in latent reasoning to perform internal computation.
- Vector representations of individual tokens from genomic foundation models; the raw inputs to sequence pooling methods.
- Lagged time series used to capture dynamical dependencies.