I have been gone a while
When I got home from SF last July I found out my Mother was diagnosed with terminal stomach cancer, this month I lost her.
Years went by where she was the only one to believe in me, I achieved my professional goals in time for her to see the path I was on, I know she was proud so I’m going to continue down it.
I am going to be in SF till the 13th, if you are interested in talking to me please reach out, my goal for this trip is to meet as many people in ml research and engineering as possible. I have just updated my personal website (noah dot jp dot net) with the relevant information!
noah retweeted
🔍 New paper: How do vision-language models actually align visual- and language representations?
We used sparse autoencoders to peek inside VLMs and found something surprising about when and where cross-modal alignment happens!
Presented at XAI4CV Workshop @ CVPR
🧵 (1/6)
noah retweeted
Sparse autoencoders (SAEs) can be used to elicit strong reasoning abilities with remarkable efficiency.
Using only 1 hour of training at $2 cost without any reasoning traces, we find a way to train 1.5B models via SAEs to score 43.33% Pass@1 on AIME24 and 90% Pass@1 on AMC23.
noah retweeted
In particular, I think the current wave of SAE skepticism is about as irrational as the wave of SAE hype that preceded it. It is wholly plausible that there are a set of improvements that will lead to massive improvements. Just, those improvements won't be found by throwing spaghetti at the wall. This is a situation where a deeper, more careful, understanding of the underlying structures is really necessary.
noah retweeted
🚨 New paper alert!
Linear representation hypothesis (LRH) argues concepts are encoded as **sparse sum of orthogonal directions**, motivating interpretability tools like SAEs. But what if some concepts don’t fit that mold? Would SAEs capture them? 🤔
1/11
noah retweeted
am i sure the death star is going down? look at my quant. look at him! you notice anything different about him? look at his eyes. i’ll give you a hint—his name’s a fucking number!! he doesn’t even speak english—it’s all beep-boop shit!! yeah, i’m sure.
A lot of alpha in this graph
remember “Large Language Models are Zero-Shot Reasoners” as well?
I love it when a plan comes together
noah retweeted
🚀 Excited to share the most inspiring work I’ve been part of this year:
"Learning to Reason without External Rewards"
TL;DR: We show that LLMs can learn complex reasoning without access to ground-truth answers, simply by optimizing their own internal sense of confidence. 1/n
noah retweeted
The more I look into the system card, the more I see over and over 'oh Anthropic is actually noticing things and telling us where everyone else wouldn't even know this was happening or if they did they wouldn't tell us.'
