finding
active
finding:predictive-and-novel-components-are-approximately-orthogonal-inner-product-0-02-across-story-web-codePredictive and novel components are approximately orthogonal (inner product ≈ -0.02) across Story, Web, Code.
Table 3.
Source paper
extracted_from(2025) · Lubana, Ekdeep Singh · Rager, Can · Hindupur, Sai Sumedh R. · Costa, Valerie +12
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- §7.2 assertion.
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.
- Table 3.
- Fig. 8b,c.
- If simulators are not inner aligned, then many important properties like prediction orthogonality may not hold.hypothesis0.777Conditional importance of inner alignment.
- Residuals of the novel component are assumed i.i.d. over time, which is still an assumption.claim0.775Acknowledged limitation.
- Table 3.
- Fig. 58.
- Distinct from internal emotion.
- At Llama layer 26 (~81% depth) the predictive component does not dominate the latent norm.finding0.760Fig. 14.