Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability
Quick summary
arXiv:2608.19338v1 Announce Type: cross Abstract: Mechanistic interpretability seeks quantities that models do not expose directly: represented states, component effects, interactions, and responses to interventions. Patching, gradients, Hessian-vector products, and subset interventions provide different measurements under different access assumptions and may target different quantities. We formulate their shared measurement structure as mechanistic tomography: designed measurement for recovering internal mechanisms and intervention effects. For a chosen basis and intervention family, measurem
Key takeaways
- arXiv:2608.19338v1 Announce Type: cross Abstract: Mechanistic interpretability seeks quantities that models do not expose directly: represented states, component effects, interactions, and responses to interventions.
- Patching, gradients, Hessian-vector products, and subset interventions provide different measurements under different access assumptions and may target different quantities.
- We formulate their shared measurement structure as mechanistic tomography: designed measurement for recovering internal mechanisms and intervention effects.
Why it matters
The importance of “Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments