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

Cerrado
  • ¿Algo no está bien?
#1,958 1 comentario 0 reacciones 0 asignados Ver en GitHub

Los mantenedores suelen responder en 1 día

@emerardd ya está trabajando en esto.

Desde el 2/11/2026.

  • #1959 de @emerardd — fusionado

Evaluación

Dificultad
3/5
Tiempo estimado
1-2 días
Aptitud para principiantes
75/100
Tipo de issue
Error
Claridad
Bien especificado
Estado de actividad
Activo
Stack tecnológico
python, pytorch
Área
tooling

Línea de trabajo

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.

Escrito por el modelo de indexación a partir del texto del issue.

Descripción

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.
Lenguaje dominante
Python
Estrellas
3.9k
Forks
708
Merge medio
1 d 4 h
PR fusionados (30 d)
87

Preparar el entorno

Abrir en Codespaces

Inicia el contenedor de desarrollo del proyecto en tu navegador, con tu propia cuenta de GitHub.

  • Sin Dockerfile ni archivo de Docker Compose
  • Tiene una plantilla de pull request
  • Sin guía de contribución

Primeros pasos

  1. Lee el issue completo y luego la guía de contribución del proyecto.
  2. Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
  3. Haz un fork del repositorio y trabaja en una rama.
  4. Abre un pull request que haga referencia al número del issue.

Más de TransformerLensOrg/TransformerLens

Todos los issues de TransformerLensOrg/TransformerLens

Issues similares

Más issues de Python

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.