we made sparse autoencoders compete with tiny softmax classifiers and the classifiers won on bits 🐐
a pure discrete code (no coefficients!) beats a top-k SAE at matched bits on SONAR, and an 800-bit hard code recovers 97.6% of gpt-2's loss
paper out now! (link in replies)
fun demo! this runs on the ontologizer work we’ve been doing.
sparse autoencoders can’t make this chart. they give you a bag of 16k latents per person. an ontologizer gives every attendee a discrete code word, which is why you get a typology instead of a feature dump.
At @WakaruLabs, we needed to decide who to prioritize talking to at EA Global. I used a truebase's residual stream activations and our library to make a color-coded ontologizer of conference attendees
At @WakaruLabs, we needed to decide who to prioritize talking to at EA Global. I used a truebase's residual stream activations and our library to make a color-coded ontologizer of conference attendees
Temple
She loves Factorio
Crack for autistic systems thinkers and engineers hyperoptimizers
Eventually she figured out in the lategame that the ultimate bottleneck is your computer’s memory and processing power to “hold state” on the entire map and gigabase, and you’d have to optimize for that
Every bottleneck you solve…creates the next bottleneck somewhere else