finding
active
finding:emotion-probe-persistence-token-0-to-token-100-correlation-in-cogito-v2-1-is-0-214-compared-to-0-099-for-random-unit-vectors-in-7168d-spaceEmotion probe persistence (token-0 to token-100 correlation) in Cogito v2.1 is 0.214, compared to 0.099 for random unit vectors in 7168D space.
Quantitative measure of emotion feature persistence vs random baseline in Cogito
Source paper
extracted_fromScott Sauers · Imago · Janus · Antra Tessera
Neighborhood — ranked by edge-count
Claims (1)
claim
- Core empirical claim distinguishing emotion persistence from generic high-variance probe persistence
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.
- Emotion probe persistence correlation of 0.214 in Cogito v2.1 vs 0.099 for random vectorsfinding0.931Quantifies emotion feature persistence above random baseline in Cogito across 240 multi-turn conversations
- Demonstrates that Cogito emotion probes are persistently active beyond what is explained by their variance alone
- Demonstrates emotion-specific persistence beyond variance effects in Cogito
- Strong positive relationship between emotion alignment and SAE feature persistence in Cogito
- SAE feature emotion subspace overlap correlates with persistence in Cogito: Spearman +0.413, p=4.4e-196finding0.817Demonstrates that SAE features more aligned with the emotion subspace are more persistent in Cogito after variance control
- Supports that persistence is genuinely tied to emotion structure rather than measurement artifact
- Shows that causal steering effects persist over long ranges for a substantial fraction of emotion probes
- Steering effect size across 35 emotion vectors correlates with probe-preference correlation at r=0.85finding0.776Emotions correlating with preference causally drive it.