Maxime Méloux
@maximemeloux.bsky.social
PhD student @LIG | Causal abstraction, interpretability & LLMs
Our new paper, "The Dead Salmons of AI interpretability", is out!
In 2009, researchers showed that standard statistical errors could detect "brain activity" in a dead salmon 🐟.
Modern XAI methods face similar issues: we find interpretable neurons and probes even in randomly initialized models.
1/X
In 2009, researchers showed that standard statistical errors could detect "brain activity" in a dead salmon 🐟.
Modern XAI methods face similar issues: we find interpretable neurons and probes even in randomly initialized models.
1/X
January 8, 2026 at 3:23 PM
Our new paper, "The Dead Salmons of AI interpretability", is out!
In 2009, researchers showed that standard statistical errors could detect "brain activity" in a dead salmon 🐟.
Modern XAI methods face similar issues: we find interpretable neurons and probes even in randomly initialized models.
1/X
In 2009, researchers showed that standard statistical errors could detect "brain activity" in a dead salmon 🐟.
Modern XAI methods face similar issues: we find interpretable neurons and probes even in randomly initialized models.
1/X
I'm very happy to present our work "Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?" this afternoon at #ICLR2025! Come have a chat at stand #439 :)
April 26, 2025 at 2:26 AM
I'm very happy to present our work "Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?" this afternoon at #ICLR2025! Come have a chat at stand #439 :)