superposition-necessitates-covariance-whitening

OUT derived (depth 2)

Created 2026-08-25T03:03:22+00:00 · Reviewed 2026-08-25T04:02:18+00:00

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.

Justifications

SL — Superposition creates the interference problem, covariance geometry is the specific algebraic solution to that problem, and the residual stream is the shared substrate where both co-occur; retracting any one breaks the logical chain

Antecedents (all must be IN):

  • OUT superposition-as-compositional-basis — Superposition is the fundamental compositional mechanism in LLMs: the 10–200× over-complete expansion (SAE), the key-value memory structure (ROME's W_fc/W_proj), and the direct-sum space decomposition (Park's polytope+orthogonality) are three independent geometric consequences of the same over-completeness.
  • IN covariance-geometry-as-canonical-tool — Independent lines of work (ROME's key-space projection and Park's unembedding whitening) converge on using empirical second-moment matrices to define the "correct" inner product for reasoning about transformer representations.
  • OUT residual-stream-universal-substrate — SAE (middle-layer residual stream), ROME (mid-layer MLP value projection), and Park (final-layer unembedding) all identify the residual stream at different depths as the primary locus of interpretable geometric structure.

Unless (any of these IN defeats this justification):

  • IN superposition-necessitates-covariance-whitening-v2 — Over-complete superposition in the residual stream (identified as a locus of interpretable structure across multiple depths) is a primary structural condition that motivates the use of empirical second-moment matrices as a natural inner product for reasoning about individual features and performing targeted interventions; independent lines of work (ROME's key-space projection, Park's unembedding whitening) converge on this covariance-geometry approach as a practical framework for feature manipulation in over-complete representation spaces.

Dependents

These beliefs depend on this one: