definition
Mechanistic interpretability reverse-engineers grown networks
Mechanistic interpretability is reverse-engineering neural networks to find their core units of computation; the field exists because neural networks are grown, not built—contrary to the assumption that we understand AI perfectly because we made it—and since Chris Olah co-founded Anthropic three and a half years ago there has been a major breakthrough roughly every six months: toy models of superposition, sparse autoencoders (Towards Monosemanticity), scaling to 30 million features on Claude 3 Sonnet, and now circuits.
definitionpending
Speaker
Trenton BrickenEvidence Quote
“Lots of people think that because we made neural networks, because they're artificial intelligence, we have a perfect understanding of how they work. It couldn't be further from the truth.”
Created: 6/13/2026, 3:28:51 AM
Your notes
Loading notes...