Dumb question — are these the same polytopes as described in Anthropic’s recent work here, or different polytopes?
No, they exist in different spaces: Polytopes in our work are in activation space whereas in their work the polytopes are in the model weights (if I understand their work correctly).
Dumb question — are these the same polytopes as described in Anthropic’s recent work here, or different polytopes?
No, they exist in different spaces: Polytopes in our work are in activation space whereas in their work the polytopes are in the model weights (if I understand their work correctly).