Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits
Quick summary
arXiv:2607.01940v3 Announce Type: replace-cross Abstract: Mechanistic interpretability seeks to explain transformer behavior through circuits: sets of internal components that causally support a behavior. However, self-repair creates a blind spot: ablating a primary component can activate a dormant backup, so a circuit that explains behavior in the intact model can become incomplete under the intervention used to test it. We formulate this gap as conditional circuit completion: given a primary set, identify components that become causally important after its removal. We introduce conditional c
Key takeaways
- arXiv:2607.01940v3 Announce Type: replace-cross Abstract: Mechanistic interpretability seeks to explain transformer behavior through circuits: sets of internal components that causally support a behavior.
- However, self-repair creates a blind spot: ablating a primary component can activate a dormant backup, so a circuit that explains behavior in the intact model can become incomplete under the intervention used to test it.
- We formulate this gap as conditional circuit completion: given a primary set, identify components that become causally important after its removal.
Why it matters
This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.
Member comments