Viewing profile — fakeparmesean
fakeparmesean
HN member- Joined
- Tue, Jan 11, 2022, 1:35 PM UTC
- HN karma
- 1
- Public activity
- 1 items
- HN profile
- View on Hacker News ↗
About fakeparmesean
No profile information was provided.
Recent public activity
-
comment
Comment #42884897
My understanding coming from mechanistic interpretability is that models are typically (or always) in superposition, meaning that most or all neurons are forced to encode semantica…