Skip to content

Redundancy mechanism: why is TE≈0 without any rewrite? (parked) #47

Open

Description

@xiaohan2012

Follow-up to #45 (self-repair falsified: CE≈0 everywhere). The dip→recover of balef2026 Exp6 is passive redundancy, not active compensation. This issue is about the next question: what is the redundancy mechanism? Parked — no work planned yet.

Where we stand

  • Ablating a layer dips a depth-m+1 tuned probe, but the answer is still decodable at the end → TE≈0.
  • Frozen-downstream DE shows no rewrite (CE = DE − TE ≈ 0; per-row unimodal at 0; CE~DE R²≤0.08; Mitra linear anchor agrees).
  • So nobody compensates — the information was already duplicated / cheaply recomputable. Untested: how.

Why TFMs plausibly differ from LLMs: the input table stays in context → recompute is cheap → no need for backup-head-style active repair.

But "DE≈0" is not one thing

margin, |·| > 0.1:

model origin-redundant (DE≈0, TE≈0) indirectly important (DE≈0, TE large)
TabFM 78% 10%
Mitra 44% 40%
TabICL 41% 40%
LimiX-2M 16% 53%
  • TabFM = cleanest subject (mostly pure redundancy).
  • LimiX-2M = least redundant — early/mid layers do necessary feature work (dip does not recover).
  • Any mechanism claim must be stated per model, not globally.

Hypotheses

  • H1 — copies exist. The same information sits in the residual at many depths.
    • test: linear probe at every depth / cross-layer representation similarity → near-ceiling decodability well before the load-bearing layers.
  • H2 — recompute from the input table. After ablating m, later layers re-derive rather than read another cached copy.
    • test: co-ablate layer m and the attention path to the input rows → recover should vanish if H2, survive if H1.
  • H3 — k-layer joint ablation (cheapest, most decisive). One layer can't remove the information; how many can?
    • genuine redundancy → TE has a threshold / phase transition in k.
    • indirect importance → TE grows linearly from k=1.
    • cost: reuses inject_delta, just inject at k layers at once. No new method.
  • H4 — who writes the copies, attention vs MLP sublayers.

Suggested order

H3 (infra already exists) → H1 (probes already exist) → H2 → H4.

Links

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions