"um by projecting it back to the residual stream um one thing to emphasize is I don't 40:32 actually like the words reading and writing here because I think they can be pretty misleading but in particular 40:38 reading and writing intuitively feel like inverses or complementary operations but they're actually very 40:44 different so I prefer the word um project for read and embed for write"
no subject
40:32
actually like the words reading and writing here because I think they can be pretty misleading but in particular
40:38
reading and writing intuitively feel like inverses or complementary operations but they're actually very
40:44
different so I prefer the word um project for read and embed for write"