superposition-covariance-editability-triangle

OUT derived (depth 4)

Created 2026-08-25T03:07:18+00:00 · Reviewed 2026-08-25T03:24:16+00:00

Superposition, covariance whitening, and rank-one editability form a closed logical triangle in which each property necessitates the others: over-complete superposition requires covariance separation for feature addressability, covariance separation defines the geometric space in which rank-one updates are well-defined, and the boundedness of rank-one editing confirms the addressable space is finite.

Justifications

SL — The three depth-2/3 geometric properties are individually stated but their mutual dependency is never made explicit; together they form a closed triangle where retracting any vertex collapses the others.

Antecedents (all must be IN):

  • OUT superposition-necessitates-covariance-whitening — Over-complete superposition in the shared residual-stream substrate is the precise structural condition that necessitates covariance/whitening (second-moment projection) as the canonical tool for isolating individual features and performing targeted rank-one edits; without superposition, raw Euclidean geometry would suffice and the entire covariance-geometry framework would be unnecessary.
  • OUT geometric-editing-addressability-bound — The covariance-geometry framework defines a precise and minimal addressable space for knowledge editing (rank-one updates to a single MLP value projection), but the combination of superposition and distributed corpus acquisition structurally bounds this to single-fact local corrections—edits cannot create novel multi-hop associations because the target knowledge was never locally consolidated in the first place.
  • OUT covariance-geometry-as-operational-semantic-space — The covariance/whitening geometry (second-moment matrices) is the operational definition of semantic coordinate space in LLMs: it simultaneously parameterises feature interpretation (SAE decoder space, Park polytopes), similarity evaluation (cosine→Spearman pipeline), and knowledge modification (ROME rank-one updates), and this structure converges across model families.

Unless (any of these IN defeats this justification):

  • IN superposition-covariance-editability-triangle-v2 — Superposition, covariance geometry, and rank-one editability form an interdependent framework in which each concept provides structural context for the others: over-complete superposition in the residual stream is the primary structural condition that makes covariance/whitening the canonical tool for feature isolation and targeted rank-one edits, covariance geometry serves as the operational coordinate space in which those rank-one updates are formulated, and the structural bounds on such edits—limited to single-fact local corrections rather than novel multi-hop associations—reflect the distributed, locally non-consolidated nature of the underlying superposed representation.

Dependents

These beliefs depend on this one: