David Udell comments on Sparse Coding, for Mechanistic Interpretability and Activation Engineering

David Udell 23 Sep 2023 19:20 UTC
4 points
0
No, towards an $L^{0}$ value. $L^{1}$ is the training proxy for that, though.
- LawrenceC 23 Sep 2023 19:21 UTC
  4 points
  0
  Parent
  Oh, okay, makes sense.