K-Means Clustering of User Messages

Clustering user message embeddings to identify categories causing persona drift vs. maintenance

Neighborhood — ranked by edge-count

paper

method

k-means clustering
related_to
Unsupervised feature-finding method using cluster centroid difference as feature direction

cosine ≥ 0.65 · no typed edge

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

Cluster 1 (4-cluster): CONTRAST, NOT-SEPARATENESS, ROUGHNESS, ALTERNATING REPETITION, GOOD SHAPEfinding0.724
First cluster of the four-cluster grouping, containing properties 9, 15, 11, 4, 6.
Unsupervised Behavior Clusteringmethod0.722
Method that clusters behaviors without prior labels, used to surface concerning learned patterns.
Behavior Clusteringconcept0.711
Grouping similar model behaviors; the unsupervised method surfaces clusters of concerning patterns.
Cluster 4 (4-cluster): SIMPLICITY AND INNER CALM, ECHOES, GRADIENTS, POSITIVE SPACEfinding0.709
Fourth cluster of the four-cluster grouping, containing properties 14, 12, 10, 5.
K-Compositionconcept0.702
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
Cluster 2 (5-cluster): ROUGHNESS, ALTERNATING REPETITION, GOOD SHAPEfinding0.691
Second cluster of the five-cluster grouping, containing properties 11, 4, 6.
k-shot promptingmethod0.690
Prompting technique where k example pairs are provided as anchors.
K values represent 'given current state, where in the future should look here?'claim0.689
Janus's interpretive claim about key vectors.