Jan 20 - 23, 2023Online and in person
Mechanistic Interpretability Hackathon
This Sprint has ended.
- Sign-ups
- 52
Projects from this Sprint are not published on the site.
Machine learning is becoming an increasingly important part of our lives and researchers are still working to understand how neural networks represent the world.
Overview
Machine learning is becoming an increasingly important part of our lives and researchers are still working to understand how neural networks represent the world.
Alignment Jam hackathons
Join us in this iteration of the Alignment Jam research hackathons to spend 48 hour with fellow engaged researchers and engineers in machine learning on engaging in this exciting and fast-moving field!
Join the Discord where all communication will happen. Check out research project ideas for inspiration and the in-depth starter resources.
Using mechanistic interpretability, we will dive deep into how neural networks think and do. We work towards reverse-engineering the information processing of artificial intelligence!
We provide you with the best starter templates that you can work from so you can focus on creating interesting research instead of browsing Stack Overflow. Check the resources out here. You're very welcome to check out some of the ideas already posted!
Local groups
If you are part of a local machine learning or AI safety group, you are very welcome to set up a local in-person site to work together with people on this hackathon! We will have several across the world (list upcoming) and hope to increase the amount of local spots. Sign up to run a jam site here.
You will work in groups of 2-6 people within our hackathon GatherTown and in the in-person event hubs.
Resources
Check out the Quickstart Guide for Mechanistic Interpretability
Mechanistic interpretability is a field focused on reverse-engineering neural networks. This can both be how Transformers do a very specific task and how models suddenly improve. Check out our speaker Neel Nanda's 200+ research ideas in mechanistic interpretability.
Speakers
Esben Kran
Organizer and Keynote Speaker
Esben is the founder of Apart Research, which he launched at age 22 after leaving grad school. Apart accelerates AI safety research worldwide, producing 20+ papers, award-winning benchmarks like DarkBench, and engaging 4,000+ hackers in research sprints.
Recently co-launched Seldon to fund critical infrastructure for humanity's future, with first investments in Andon Labs, Lucid Computing, Workshop Labs, and Asymmetric Security.
Neel Nanda
Speaker & Judge
Team lead for the mechanistic interpretability team at Google Deepmind and a prolific advocate for open source interpretability research.
Local sites
AI Neuroscience Global
Join in for the global Gathertown for the Alignment Jam
Event page: AI Neuroscience Global (opens in new tab)Budapest Mechanistic Interpretability Hackathon
Interpretability Hackathon with EA Budapest and the Budapest AI Safety Group, supported by AlignmentJam
Event page: Budapest Mechanistic Interpretability Hackathon (opens in new tab)Cambridge Mechanistic Interpretabiltiy Hackathon
Cambridge AI Safety Hub will host a jam site at the Sidney Street Office, 2nd floor in Cambridge.
Carnegie AI Safety Initiative: ML Interpretability Hackathon
The Carnegie AI Safety Initiative is hosting a jam site at Carnegie Mellon University. Click the link to join their Discord and stay updated!
Event page: Carnegie AI Safety Initiative: ML Interpretability Hackathon (opens in new tab)CompSoc Mechanistic Interpretability Hackathon
We'll be at the Appleton Tower on the Edinburgh campus. 11 Crichton St, Newington, Edinburgh EH8 9LE,
Copenhagen Mechanistic Interpretabilty Hackathon
effective-altruism-denmark
Apart is hosting a jam site in Copenhagen for the universities in Station Copenhagen.
Event page: Copenhagen Mechanistic Interpretabilty Hackathon (opens in new tab)Ens Ulm interpretability hackathon
Salle Bourbaki pour samedi et dimanche. Mechanistic interpretability hackathon at Ulm organized by EffiSciences.
Event page: Ens Ulm interpretability hackathon (opens in new tab)LEAH Mechanistic Interpretability Hackathon
LEAH is hosting the mechanistic interpretability hackathon for the London Univeristies.
Mentaleap Mechanistic Interpretability Hackathon
EA Israel and the Mentaleap team will host a location in Israel: Hackers, neuroscientists, AI experts.
OxAI Mechanistic Interpretability Hackathon
Oxford AI Safety Hub and OxAI will host a jam site in Oxford.
SAIA Mechanistic Interpretability Hackathon
The Stanford AI Alignment group is hosting a jam site for this month's mechanistic interpretability hackathon at a campus room to be announced by Stanford AI Alignment.
Uppsala Mechanistic Interpretability Jam
We will be in a room (still undecided) at Ångströmlaboratoriet.
Event page: Uppsala Mechanistic Interpretability Jam (opens in new tab)
Where a Sprint can lead
How our programs connectAnyone can join
Stand out
6 to 16 weeks on your own project, with a research project manager, compute and publication support.
Upcoming Sprints
All SprintsAI Collusion Research Sprint
A weekend research sprint on collusion between AI agents: when it emerges in markets and everyday workflows, how to detect and audit it, how it is carried, and what breaks it. Co-organized with Poseidon Research and AE Studio, online with in-person hubs at Collider in New York City and AI Safety Hong Kong. Top teams are invited to apply to the Apart Fellowship.
Read the brief: AI Collusion Research SprintAI x Epistemics Research Sprint
A weekend research sprint on AI for epistemics: evaluating whether models know how solid their claims are, building trust infrastructure that people and agents can consume, and shipping epistemic products that improve real decisions. Online, four tracks including an open track. Top teams are invited to apply to the Apart Fellowship.
Read the brief: AI x Epistemics Research SprintQuestions? sprints@apartresearch.com