ACL Time @ Bangkok 🇹🇭 Our GNNavi work will be presented in the poster session at 12:30 on Aug. 14 (Wed.). Welcome to drop by and exchange with us! Looking forward to talking with people, especially those who are interested in multilingual & low-resource & LLM interpretability🤗

We're open-sourcing Sparse Autoencoders (SAEs) for Llama 3.3 70B and Llama 3.1 8B! These are, to the best of our knowledge, the first open-source SAEs for models at this scale and capability level.

What can AI researchers do *today* that AI developers will find useful for ensuring the safety of future advanced AI systems? To ring in the new year, the Anthropic Alignment Science team is sharing some thoughts on research directions we think are important.

This Thursday (in 3 days), Yishay Mansour will discuss interpretable approximations — learning with interpretable models. Is it the same as regular learning? Attend the lecture to find out! 💻 Website: tverven.github.io/tiai-seminar/ Suraj Srinivas @ ICML Tim van Erven

Chirag Agarwal Follow us for AI safety insights x.com/intent/follow?… And watch the full video youtu.be/nqZ6EiPltSo&li…

LLMs are all circuits and patterns Nice Paper for a long weekend read - "A Primer on the Inner Workings of Transformer-based Language Models" 📌 Provides a concise intro focusing on the generative decoder-only architecture. 📌 Introduces the Transformer layer components,

Dylan Sam Hi Dylan, it reminds me of our paper where we also train a model (model 2) on the output of another black-box model (model 1). ultimately we find that combining the outputs of model 2 and model 1 helps improve the perf significantly. openreview.net/forum?id=OcFjq…

In case you missed it: here is the recording of Yishay Mansour's talk about the ability of decision trees to approximate concepts: youtu.be/uOwuho2er58 For upcoming talks, check out the seminar website: tverven.github.io/tiai-seminar/

This week's Apart News brings you an *exclusive* interview with interpretability insider Myra Deng of Goodfire & revisits our Sparse Autoencoders Hackathon which featured a memorable talk from Google DeepMind's Neel Nanda.

The later features in DINO-v2 are more abstract and semantically meaningful than I'd expected from the training objectives. This neuron responds only to hugs. Nothing else, just hugs.

🔍 Curious about what's really happening inside vision models? Join us at the First Workshop on Mechanistic Interpretability for Vision (MIV) at #CVPR2025! 📢 Website: sites.google.com/view/miv-cvpr2… Meet our amazing invited speakers! #CVPR2025 #MIV25 #MechInterp #ComputerVision

We have moved to 🦋 bluesky! Please follow over there @ XAI-Research bsky.app/profile/xai-re…

Exciting opportunity at the intersection of climate science and XAI to work on groundbreaking research in attributing extreme precipitation events with multimodal models. Check out the details and help spread the word! #ClimateAI #Postdoc #UVA #Hiring Job description:

Reminder we have moved to 🦋 Stay up to date with the latest XAI research!

Hot off the press: my PhD thesis "Foundations of machine learning interpretability" is officially published! Enjoy it at theses.hal.science/tel-04917007 Explainable AI Trustworthy ML Initiative (TrustML)

Super excited to share our latest preprint that unifies multiple areas within explainable AI that have been evolving somewhat independently: 1. Feature Attribution 2. Data Attribution 3. Model Component Attribution (aka Mechanistic Interpretability) arxiv.org/abs/2501.18887

🚨 Excited to share: "Learning to Generate Unit Tests for Automated Debugging" 🚨 which introduces ✨UTGen and UTDebug✨ for teaching LLMs to generate unit tests (UTs) and debugging code from generated tests. UTGen+UTDebug improve LLM-based code debugging by addressing 3 key

Our Theory of Interpretable AI (tverven.github.io/tiai-seminar/) will soon celebrate its one-year anniversary! 🥳 As we step into our second year, we’d love to hear from you! What papers would you like to see discussed in our seminar in the future? 📚🔍 Tim van Erven Michal Moshkovitz