I'll be attending #ICLR2026 next week to present my work on In-Context Algebra! My poster will be on Fri, April 24 at 3:15-5:45PM at Pavilion 4 P4-#4011. If you're around, stop by and say hello! My DMs are open if you want to connect or meet up in Rio! bsky.app/profile/eri...

Eric Todd (@ericwtodd.bsky.social)

Can you solve this algebra puzzle? 🧩 cb=c, ac=b, ab=? A small transformer can learn to solve problems like this! And since the letters don't have inherent meaning, this lets us study how context alone imparts meaning. Here's what we found:🧵⬇️

bsky.app

New paper: LLMs encode harmful content generation in a distinct, unified mechanism Using weight pruning, we find that harmful generation depends on a tiny subset of the weights that are shared across harm types and separate from benign capabilities. 🧵

The Art of Wanting. About the question I see as central in AI ethics, interpretability, and safety. Can an AI take responsibility? I do not think so, but *not* because it's not smart enough. davidbau.com/archives/20...

Can models understand each other's reasoning? 🤔 When Model A explains its Chain-of-Thought (CoT) , do Models B, C, and D interpret it the same way? Our new preprint with @davidbau.bsky.social and @csinva.bsky.social explores CoT generalizability 🧵👇 (1/7)

Can you solve this algebra puzzle? 🧩 cb=c, ac=b, ab=? A small transformer can learn to solve problems like this! And since the letters don't have inherent meaning, this lets us study how context alone imparts meaning. Here's what we found:🧵⬇️

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.

LLMs have been shown to provide different predictions in clinical tasks when patient race is altered. Can SAEs spot this undue reliance on race? 🧵 Work w/ @byron.bsky.social Link: arxiv.org/abs/2511.00177

Interested in doing a PhD at the intersection of human and machine cognition? ✨ I'm recruiting students for Fall 2026! ✨ Topics of interest include pragmatics, metacognition, reasoning, & interpretability (in humans and AI). Check out JHU's mentoring program (due 11/15) for help with your SoP 👇

JHU Cognitive Science@jhucogsci.bsky.social · 9mo ago

The department of Cognitive Science @jhu.edu is seeking motivated students interested in joining our interdisciplinary PhD program! Applications due 1 Dec Our PhD students also run an application mentoring program for prospective students. Mentoring requests due November 15. tinyurl.com/2nrn4jf9

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)! 🧵

Looking forward to attending #COLM2025 this week! Would love to meet up and chat with others about interpretability + more. DMs are open if you want to connect. Be sure to checkout @sfeucht.bsky.social's very cool work on understanding concepts in LLMs tomorrow morning (Poster 35)!

Sheridan Feucht@sfeucht.bsky.social · last yr.

[📄] Are LLMs mindless token-shifters, or do they build meaningful representations of language? We study how LLMs copy text in-context, and physically separate out two types of induction heads: token heads, which copy literal tokens, and concept heads, which copy word meanings.

What's the right unit of analysis for understanding LLM internals? We explore in our mech interp survey (a major update from our 2024 ms). We’ve added more recent work and more immediately actionable directions for future work. Now published in Computational Linguistics!

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...

Announcing a broad expansion of the National Deep Inference Fabric. This could be relevant to your research...

"AI slop" seems to be everywhere, but what exactly makes text feel like "slop"? In our new work (w/ @tuhinchakr.bsky.social, Diego Garcia-Olano, @byron.bsky.social ) we provide a systematic attempt at measuring AI "slop" in text! arxiv.org/abs/2509.19163 🧵 (1/7)

Wouldn’t it be great to have questions about LM internals answered in plain English? That’s the promise of verbalization interpretability. Unfortunately, our new paper shows that evaluating these methods is nuanced—and verbalizers might not tell us what we hope they do. 🧵👇1/8

This Friday NEMI 2025 is at Northeastern in Boston, 8 talks, 24 roundtables, 90 posters; 200+ attendees. Thanks to goodfire.ai/ for sponsoring! nemiconf.github.io/summer25/ If you can't make it in person, the livestream will be here: www.youtube.com/live/4BJBis...

New England Mechanistic Interpretability Workshop

About:The New England Mechanistic Interpretability (NEMI) workshop aims to bring together academic and industry researchers from the New England and surround...

youtube.com

We've added a quick new section to this paper, which was just accepted to @COLM_conf! By summing weights of concept induction heads, we created a "concept lens" that lets you read out semantic information in a model's hidden states. 🔎

Sheridan Feucht@sfeucht.bsky.social · last yr.

[📄] Are LLMs mindless token-shifters, or do they build meaningful representations of language? We study how LLMs copy text in-context, and physically separate out two types of induction heads: token heads, which copy literal tokens, and concept heads, which copy word meanings.

Im excited for NEMI again this year! I’ve enjoyed local research meetups and getting to know others near me working on interesting problems.

Koyena Pal@koyena.bsky.social · last yr.

🚨 Registration is live! 🚨 The New England Mechanistic Interpretability (NEMI) Workshop is happening Aug 22nd 2025 at Northeastern University! A chance for the mech interp community to nerd out on how models really work 🧠🤖 🌐 Info: nemiconf.github.io/summer25/ 📝 Register: forms.gle/v4kJCweE3UUH...

🚨 Registration is live! 🚨 The New England Mechanistic Interpretability (NEMI) Workshop is happening Aug 22nd 2025 at Northeastern University! A chance for the mech interp community to nerd out on how models really work 🧠🤖 🌐 Info: nemiconf.github.io/summer25/ 📝 Register: forms.gle/v4kJCweE3UUH...

How do language models track mental states of each character in a story, often referred to as Theory of Mind? We reverse-engineered how LLaMA-3-70B-Instruct handles a belief-tracking task and found something surprising: it uses mechanisms strikingly similar to pointer variables in C programming!

Can we uncover the list of topics a language model is censored on? Refused topics vary strongly among models. Claude-3.5 vs DeepSeek-R1 refusal patterns:

I'll present a poster for this work at NENLP tomorrow! Come find me at poster #80...

Sheridan Feucht@sfeucht.bsky.social · last yr.

[📄] Are LLMs mindless token-shifters, or do they build meaningful representations of language? We study how LLMs copy text in-context, and physically separate out two types of induction heads: token heads, which copy literal tokens, and concept heads, which copy word meanings.

Sheridan asks whether the Dual Route Model of Reading that psychologists have observed in humans also appears in LLMs. In her brilliantly simple study of induction heads, she finds that it does! Induction has a Dual Route that separates concepts from literal token processing. Worth reading ↘️

Sheridan Feucht@sfeucht.bsky.social · last yr.

[📄] Are LLMs mindless token-shifters, or do they build meaningful representations of language? We study how LLMs copy text in-context, and physically separate out two types of induction heads: token heads, which copy literal tokens, and concept heads, which copy word meanings.

[📄] Are LLMs mindless token-shifters, or do they build meaningful representations of language? We study how LLMs copy text in-context, and physically separate out two types of induction heads: token heads, which copy literal tokens, and concept heads, which copy word meanings.

What will be the linchpin for AI dominance? Read our NSF/OSTP recommendations written with Goodfire's Tom McGrath tommcgrath.github.io, Transluce's Sarah Schwettmann cogconfluence.com, MIT's Dylan Hadfield-Menell @dhadfieldmenell.bsky.social TLDR; Dominance comes from **interpretability** 🧵 ↘️

I'm searching for some comp/ling experts to provide a precise definition of “slop” as it refers to text (see: corp.oup.com/word-of-the-...) I put together a google form that should take no longer than 10 minutes to complete: forms.gle/oWxsCScW3dJU... If you can help, I'd appreciate your input! 🙏

Oxford Word of the Year 2024 - Oxford University Press

The Oxford Word of the Year 2024 is 'brain rot'. Discover more about the winner, our shortlist, and 20 years of words that reflect the world.

corp.oup.com

Induction heads are commonly associated with in-context learning, but are they the primary driver of ICL at scale? We find that recently discovered "function vector" heads, which encode the ICL task, are the actual primary mechanisms behind few-shot ICL! arxiv.org/abs/2502.14010 🧵👇

LLMs are known to perpetuate social biases in clinical tasks. Can we locate and intervene upon LLM activations that encode patient demographics like gender and race? 🧵 Work w/ @arnabsensharma.bsky.social, @silvioamir.bsky.social, @davidbau.bsky.social, @byron.bsky.social arxiv.org/abs/2502.13319

Please help amplify ARBOR, a fantastic new research opportunity! If you’d like to start contributing, NDIF is now hosting DeepSeek R1 8B and 70B, open for all researchers to experiment on via our API. Sign up for API access here: login.ndif.us

Today we launch a new open research community It is called ARBOR: arborproject.github.io/ please join us. bsky.app/profile/ajy...

I'm excited about this new open research initiative! It kind of feels like this is how science is supposed to be done - collaborating and sharing ideas in the open. If you've thought about studying the mechanisms behind R1 & other reasoning models check it out!

Today we launch a new open research community It is called ARBOR: arborproject.github.io/ please join us. bsky.app/profile/ajy...