Noticed thad I didn’t answer Kaarel’s question there in a satisfactory way. Yeah—“basin” here is meant very informally as a local piece of the loss landscape with lower loss than the rest of the landscape, and surrounding a subspace of weight space corresponding to a circuit being on. Nina and I actually call this a “valley” our “low-hanging fruit” post.
By “smaller” vs. “larger” basins I roughly mean the same thing as the notion of “efficiency” that we later discuss
Noticed thad I didn’t answer Kaarel’s question there in a satisfactory way. Yeah—“basin” here is meant very informally as a local piece of the loss landscape with lower loss than the rest of the landscape, and surrounding a subspace of weight space corresponding to a circuit being on. Nina and I actually call this a “valley” our “low-hanging fruit” post.
By “smaller” vs. “larger” basins I roughly mean the same thing as the notion of “efficiency” that we later discuss