A good thread on the current state of SAEs - useful, certainly

Press Space to continue

A good thread on the current state of SAEs - useful, certainly not dead, but not enough alone

Are SAEs dead? Will they save us from neuralese? Should I just use a probe? We get these questions all the time. Part 2 of our educational series on applied interpretability explains what SAEs are good for, when *not* to use them, and what to use instead. 🧵 https://t.co/hVSvLY0xeP