definition
Linear representation hypothesis
The linear representation hypothesis holds that directions in activation space have meaning — the more a feature (a direction) fires, the more the model believes that concept is present — which is why word arithmetic works (king − man + woman ≈ queen), and which gives weights a clean interpretation as meaningful edges.
definitionpending
Speaker
Chris OlahEvidence Quote
“it’s really about this property of being able to add things together, that you can independently modify, say gender and royalty, or cuisine type, or country, and the concept of food by adding them.”
Created: 6/13/2026, 3:36:36 AM
My Notes
Loading notes...