Reposted by Kerem Sahin
Humans and LLMs think fast and slow. Do SAEs recover slow concepts in LLMs? Not really.
Our Temporal Feature Analyzer discovers contextual features in LLMs, that detect event boundaries, parse complex grammar, and represent ICL patterns.
Our Temporal Feature Analyzer discovers contextual features in LLMs, that detect event boundaries, parse complex grammar, and represent ICL patterns.
November 13, 2025 at 10:32 PM
Humans and LLMs think fast and slow. Do SAEs recover slow concepts in LLMs? Not really.
Our Temporal Feature Analyzer discovers contextual features in LLMs, that detect event boundaries, parse complex grammar, and represent ICL patterns.
Our Temporal Feature Analyzer discovers contextual features in LLMs, that detect event boundaries, parse complex grammar, and represent ICL patterns.
Reposted by Kerem Sahin
How can a language model find the veggies in a menu?
New pre-print where we investigate the internal mechanisms of LLMs when filtering on a list of options.
Spoiler: turns out LLMs use strategies surprisingly similar to functional programming (think "filter" from python)! 🧵
New pre-print where we investigate the internal mechanisms of LLMs when filtering on a list of options.
Spoiler: turns out LLMs use strategies surprisingly similar to functional programming (think "filter" from python)! 🧵
November 4, 2025 at 5:48 PM
How can a language model find the veggies in a menu?
New pre-print where we investigate the internal mechanisms of LLMs when filtering on a list of options.
Spoiler: turns out LLMs use strategies surprisingly similar to functional programming (think "filter" from python)! 🧵
New pre-print where we investigate the internal mechanisms of LLMs when filtering on a list of options.
Spoiler: turns out LLMs use strategies surprisingly similar to functional programming (think "filter" from python)! 🧵
Reposted by Kerem Sahin
Who is going to be at #COLM2025?
I want to draw your attention to a COLM paper by my student @sfeucht.bsky.social that has totally changed the way I think and teach about LLM representations. The work is worth knowing.
And you can meet Sheridan at COLM, Oct 7!
bsky.app/profile/sfe...
I want to draw your attention to a COLM paper by my student @sfeucht.bsky.social that has totally changed the way I think and teach about LLM representations. The work is worth knowing.
And you can meet Sheridan at COLM, Oct 7!
bsky.app/profile/sfe...
September 27, 2025 at 8:54 PM
Who is going to be at #COLM2025?
I want to draw your attention to a COLM paper by my student @sfeucht.bsky.social that has totally changed the way I think and teach about LLM representations. The work is worth knowing.
And you can meet Sheridan at COLM, Oct 7!
bsky.app/profile/sfe...
I want to draw your attention to a COLM paper by my student @sfeucht.bsky.social that has totally changed the way I think and teach about LLM representations. The work is worth knowing.
And you can meet Sheridan at COLM, Oct 7!
bsky.app/profile/sfe...
Reposted by Kerem Sahin
1/6 🦉Did you know that telling a language model that it loves the number 087 also makes it love owls?
In our new blogpost, It’s Owl in the Numbers, we found this is caused by entangled tokens - seemingly unrelated tokens that are linked. When you boost one, you boost the other.
owls.baulab.info/
In our new blogpost, It’s Owl in the Numbers, we found this is caused by entangled tokens - seemingly unrelated tokens that are linked. When you boost one, you boost the other.
owls.baulab.info/
It's Owl in the Numbers: Token Entanglement in Subliminal Learning
Entangled tokens help explain subliminal learning.
owls.baulab.info
August 6, 2025 at 9:30 PM
1/6 🦉Did you know that telling a language model that it loves the number 087 also makes it love owls?
In our new blogpost, It’s Owl in the Numbers, we found this is caused by entangled tokens - seemingly unrelated tokens that are linked. When you boost one, you boost the other.
owls.baulab.info/
In our new blogpost, It’s Owl in the Numbers, we found this is caused by entangled tokens - seemingly unrelated tokens that are linked. When you boost one, you boost the other.
owls.baulab.info/