geometric-editing-addressability-bound

OUT derived (depth 3)

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

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.

Justifications

SL — Covariance geometry defines the editing mechanism; distributed acquisition explains why the target may not be locally consolidated; superposition explains why perturbing one superposed feature necessarily bleeds into others—together they form a complete explanation of why editing is bounded

Antecedents (all must be IN):

  • OUT covariance-geometry-unifies-analysis-and-editing — The mathematically principled framework for both interpreting (SAE feature extraction, Park polytope analysis) and modifying (ROME rank-one edits) LLM representations is second-moment covariance geometry applied to the residual stream, since C = KKᵀ whitening defines the canonical coordinate system in which all three operations become linear algebra on the same substrate.
  • OUT distributed-acquisition-bounds-editing-scope — Knowledge editing is fundamentally a correction mechanism (fixing mis-encoded local associations) rather than a creation mechanism, because novel factual knowledge requires the distributed corpus exposure that a single rank-one update on one MLP layer cannot replicate.
  • 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.

Dependents

These beliefs depend on this one: