Chandan Singh

We’ve discovered a literal miracle with almost unlimited potential and it’s being scrapped for *no reason whatsoever*. This isn’t even nihilism, it’s outright worship of death and human suffering.

Binz et al. (in press, Nature) developed an LLM called Centaur that better predicts human responses in 159 of 160 behavioural experiments compared to existing cognitive models. See: arxiv.org/abs/2410.20268

We're excited about self-play unlocking continuously improving agents. RL selects CoT patterns from LLMs. Games=perfect testing grounds.
SPIRAL: models learn via self-competition. Kuhn Poker → +8.7% math, +18.1 Minerva Math! 🃏
Paper: huggingface.co/papers/2506....
Code: github.com/spiral-rl/spiral

🚨 New preprint 🚨

Prior work has mapped how the brain encodes concepts: If you see fire and smoke, your brain will represent the fire (hot, bright) and smoke (gray, airy). But how do you encode features of the fire-smoke relation? We analyzed fMRI with embeddings extracted from LLMs to find out 🧵

Dimensions underlying the representational alignment of deep neural networks with humans - Nature Machine Intelligence An interpretability framework that compares how humans and deep neural networks process images has been presented. Their findings reveal that, unlike humans, deep neural networks focus more on visual ...

What makes humans similar or different to AI? In a paper out in @natmachintell.nature.com led by @florianmahner.bsky.social & @lukasmut.bsky.social, w/ Umut Güclü, we took a deep look at the factors underlying their representational alignment, with surprising results.

www.nature.com/articles/s42...

🚨Paper alert!🚨
TL;DR first: We used a pre-trained deep neural network to model fMRI data and to generate images predicted to elicit a large response for each many different parts of the brain. We aggregate these into an awesome interactive brain viewer: piecesofmind.psyc.unr.edu/activation_m...

What are the organizing dimensions of language processing?

We show that voxel responses during comprehension are organized along 2 main axes: processing difficulty & meaning abstractness—revealing an interpretable, topographic representational basis for language processing shared across individuals

When it comes to text prediction, where does one LM outperform another? If you've ever worked on LM evals, you know this question is a lot more complex than it seems. In our new #acl2025 paper, we developed a method to find fine-grained differences between LMs:

🧵1/9

Novel color via stimulation of individual photoreceptors at population scale Image display by cell-by-cell retina stimulation, enabling colors impossible to see under natural viewing.

Five people have seen a color never before visible to the naked human eye, thanks to a new retinal stimulation technique called Oz.

Learn more in #ScienceAdvances: scim.ag/442Hjn6

This is figure 2 from “Phase I/II trial of iPS-cell-derived dopaminergic cells for Parkinson’s disease,” which shows chronological changes in clinical end points.

Two clinical trials reported in Nature demonstrate the safety of stem cell therapies for Parkinson’s disease. The papers investigate the use of cells derived from human induced pluripotent stem cells and human embryonic stem cells. go.nature.com/4ikcJc2
go.nature.com/4jfSRYX 🧪

Accelerated learning of a noninvasive human brain-computer interface via manifold geometry Brain-computer interfaces (BCIs) promise to restore and enhance a wide range of human capabilities. However, a barrier to the adoption of BCIs is how long it can take users to learn to control them. W...

New preprint! Excited to share our latest work “Accelerated learning of a noninvasive human brain-computer interface via manifold geometry” ft. outstanding former undergraduate Chandra Fincke, @glajoie.bsky.social, @krishnaswamylab.bsky.social, and @wutsaiyale.bsky.social's Nick Turk-Browne 1/8

New preprint “Monkey See, Model Knew: LLMs accurately predict visual responses in humans AND NHPs”
Led by Colin Conwell with @emaliemcmahon.bsky.social Akshay Jagadeesh, Kasper Vinken @amrahs-inolas.bsky.social @jacob-prince.bsky.social George Alvarez @taliakonkle.bsky.social & Marge Livingstone 1/n

Human neural dynamics of real-world and imagined navigation - Nature Human Behaviour Seeber et al. studied brain recordings from implanted electrodes in freely moving humans. Neural dynamics encoded actual and imagined routes similarly, demonstrating parallels between navigational, im...

🚨 New lab paper!🚨

A dream study of mine for nearly 20 yrs not possible until now thanks to NIH 🧠 funding & 1st-author lead @seeber.bsky.social

We tracked hippocampal activity as people walked memory-guided paths & imagined them again. Did brain patterns reappear?🧵👇

www.nature.com/articles/s41...

Sanity Checks for Saliency Maps Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, Been Kim Saliency methods have emerged as a popular tool to highlight features in an input deemed relevant for the prediction of a learned model. Several saliency methods have been proposed, often guided by visual appeal on image data. In this work, we propose an actionable methodology to evaluate what kinds of explanations a given method can and cannot provide. We find that reliance, solely, on visual assessment can be misleading. Through extensive experiments we show that some existing saliency methods are independent both of the model and of the data generating process. Consequently, methods that fail the proposed tests are inadequate for tasks that are sensitive to either data or model, such as, finding outliers in the data, explaining the relationship between inputs and outputs that the model learned, and debugging the model. We interpret our findings through an analogy with edge detection in images, a technique that requires neither training data nor model. Theory in the case of a linear model and a single-layer convolutional neural network supports our experimental findings.

Sparse Autoencoders Can Interpret Randomly Initialized Transformers Thomas Heap, Tim Lawson, Lucy Farnik, Laurence Aitchison Sparse autoencoders (SAEs) are an increasingly popular technique for interpreting the internal representations of transformers. In this paper, we apply SAEs to 'interpret' random transformers, i.e., transformers where the parameters are sampled IID from a Gaussian rather than trained on text data. We find that random and trained transformers produce similarly interpretable SAE latents, and we confirm this finding quantitatively using an open-source auto-interpretability pipeline. Further, we find that SAE quality metrics are broadly similar for random and trained transformers. We find that these results hold across model sizes and layers. We discuss a number of number interesting questions that this work raises for the use of SAEs and auto-interpretability in the context of mechanistic interpretability.

2018: Saliency maps give plausible interpretations of random weights, triggering skepticism and catalyzing the mechinterp cultural movement, which now advocates for SAEs.

2025: SAEs give plausible interpretations of random weights, triggering skepticism and ...

Yi Ma & colleagues managed to simplify DINO & DINOv2 by removing many ingredients and adding a robust regularization term from information theory (coding rate) that learn informative decorrelated features. Happy to see principled approaches advance deep representation learning!

Can LLMs be used to discover interpretable models of human and animal behavior?🤔

Turns out: yes!

Thrilled to share our latest preprint where we used FunSearch to automatically discover symbolic cognitive models of behavior.
1/12

"...responses of V4 neurons under naturalistic conditions can be explained by a hierarchical three-stage model where each stage consists entirely of units like those found in area V1"

#NeuroAI

www.biorxiv.org/content/10.1...

Hi, could you possibly add me? Thanks!

At NeurIPS this week, presenting our work on crafting *interpretable embeddings* by asking yes/no questions to black-box LLMs.

Drop me a message if you want to chat about interpretability/language neuroscience!

I tried to find everyone who works in the area but I certainly missed some folks so please lmk...
go.bsky.app/BYkRryU

Science faces an explainability crisis: ML models can predict many natural phenomena but can't explain them

We tackle this issue in language neuroscience by using LLMs to generate *and validate* explanations with targeted follow-up experiments

Mechanistic interp has made cool findings but struggled to make them useful

We show that "induction heads" found in LLMs can be reverse-engineered to yield accurate & interpretable next-word prediction models