method
active
method:k-means-clustering-of-user-messagesK-Means Clustering of User Messages
Clustering user message embeddings to identify categories causing persona drift vs. maintenance
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- k-means clusteringrelated_toUnsupervised feature-finding method using cluster centroid difference as feature direction
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.
- Used to analyze emotion vector geometry.
- Intuitive groupings.
- Cluster 1 (4-cluster): CONTRAST, NOT-SEPARATENESS, ROUGHNESS, ALTERNATING REPETITION, GOOD SHAPEfinding0.724First cluster of the four-cluster grouping, containing properties 9, 15, 11, 4, 6.
- Method that clusters behaviors without prior labels, used to surface concerning learned patterns.
- Cluster features by activation statistics to get higher-level behaviors.
- Grouping similar model behaviors; the unsupervised method surfaces clusters of concerning patterns.
- Fourth cluster of the four-cluster grouping, containing properties 14, 12, 10, 5.
- A form of attention head composition where W_K reads from a subspace affected by a previous head; central to how induction heads are implemented