"Sparse autoencoders / SAEs" - if you run into this jargon, it just means "capability to analyse a complicated issue into multiple simpler components". Basically middle-school reasoning / critical thinking / analytical philosophy.
However, with regards to the implementation of SAEs in "transformer" architectures, it just gives you a better stochastic parrot, as it doesn't introduce things like rules or logic programming at all. It's just an increase in the resolution of a probabilistic reasoning algorithm.
No comments :
Post a Comment