[Bug Report] NormMatchedPlacebo silently loses norm matching and produces float16 NaNs

Chiusa
  • Qualcosa non va?
#1,958 1 commento 0 reazioni 0 assegnatari Vedi su GitHub

I maintainer di solito rispondono entro 1 giorno

@emerardd ci sta già lavorando.

Dal 2/11/2026.

  • #1959 di @emerardd — integrata

Valutazione

Difficoltà
3/5
Tempo stimato
1-2 giorni
Idoneità per principianti
75/100
Tipo di issue
Bug
Chiarezza
Specificata chiaramente
Stato di attività
Attiva
Stack tecnologico
python, pytorch
Ambito
tooling

Direzione di ricerca

Start in transformer_lens/tools/analysis/interchange.py at NormMatchedPlacebo.__call__. Reproduce with the provided torch script to see float16 NaNs and zero-projection silence. Edit to preserve zero-reference rows, normalize at safe precision, and raise on zero placebo projection with nonzero reference. Run the focused regression tests (8 failing) until they pass and new identity/error cases hold.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

Describe the bug

NormMatchedPlacebo promises to match the reference intervention's displacement in a different subspace, but a zero projection silently produces no displacement in float32 even when the reference moves. In float16, the 1e-8 denominator clamp rounds to zero and produces NaNs, including when source and base are identical. This can occur with the documented random-neuron control excluding the reference neurons, not just a degenerate dense random basis.

Code example

import torch
from transformer_lens.tools.analysis.interchange import (
    NormMatchedPlacebo, SubspaceInterchange, neuron_basis, random_neuron_basis,
)

for dtype in (torch.float32, torch.float16):
    base = torch.zeros(2, 4, dtype=dtype)
    source = base.clone()
    source[0, 0] = 2
    reference = SubspaceInterchange(neuron_basis(4, [0]))
    control_basis = random_neuron_basis(4, 1, seed=0, exclude=[0])
    result = NormMatchedPlacebo(reference, control_basis)(base, source)
    print(dtype, (reference(base, source) - base).norm(dim=-1), result)

The reference displacement norms are [2, 0]. Float32 returns two unchanged rows, so the first row is not norm-matched. Float16 returns NaNs in both rows; the second row should simply be an identity control. The current implementation also forms a potentially overflowing low-precision scale factor before multiplying by the direction.

Expected behavior: safely preserve rows with zero reference displacement, normalize nonzero projected directions at safe precision, and explicitly reject a zero placebo projection when the reference displacement is nonzero rather than silently returning an unmatched control. This keeps the existing projected-direction definition without inventing a fallback direction.

System Info

Source checkout at dev commit a7b3213a, Windows, Python 3.12, existing uv project environment, CPU. No model loading or downloads are required. Focused regression tests on this base: 8 failed, 14 passed, 38 deselected, covering float16, bfloat16, float32 and float64. Four failures assert the proposed explicit-error contract; the other four expose current float16 NaNs.

Additional context

The affected implementation is transformer_lens/tools/analysis/interchange.py, NormMatchedPlacebo.__call__. Existing random dense float32 tests cover ordinary nonzero projections, but not the zero-projection or float16 identity cases. This concerns the numerical validity of the control; no pretrained-model accuracy claim is involved.

Checklist
  • I have checked that there is no similar issue in the repo.
Lingua principale
Python
Stelle
3.9k
Fork
708
Merge medio
1g 9h
PR unite (30g)
84

Preparare l'ambiente

Apri in Codespaces

Avvia il container di sviluppo del progetto nel browser, con il tuo account GitHub.

  • Nessun Dockerfile né file Docker Compose
  • Ha un modello di pull request
  • Nessuna guida per i contributori

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di TransformerLensOrg/TransformerLens

Tutte le issue di TransformerLensOrg/TransformerLens

Issue simili

Altre issue su Python

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.