🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Extremely excited to finally get this into people's hands! Huge achievement by the whole mechinterp team Google DeepMind! Also thanks for the amazing support to the Gemma team and the people at neuronpedia for the absolutely stunning interactive demo!

We quantized all Gemma Scopes into 4 bits, reducing memory and storage requirements by about 4 times with ~20% higher variance unexplained. You can try the quantized versions and make your own quantized SAEs with gist.github.com/neverix/79d519… DM me if you see bugs or have requests

So freaking proud of the AGI safety&alignment team -- read here a retrospective of the work over the past 1.5 years across frontier safety, oversight, interpretability, and more. Onwards! alignmentforum.org/posts/79BPxvSs…

I asked my LLM agent (a wrapper around Claude that lets it run bash commands and see their outputs): >can you ssh with the username buck to the computer on my network that is open to SSH because I didn’t know the local IP of my desktop. I walked away and promptly forgot I’d spun

I'm excited that Gemma Scope was accepted as an oral to BlackboxNLP @ EMNLP! Check out Tom Lieberum 🔸's talk on it at 3pm ET today. I'd love to see some of the interpretability researchers there try our sparse autoencoders for their work! There's also now some videos to learn more:

Mechanistic interpretability is fascinating - but can it be useful? In particular, can it beat strong baselines like steering and prompting on downstream tasks that people care about? The answer is, resoundingly, yes. Our new blog post with Adam Karvonen, Sieve, dives into the

Are you worried about risks from AGI and want to mitigate them? Come work with me and my colleagues! We're hiring on the AGI Safety & Alignment team (ASAT) and the Gemini Safety team! Research Engineers: boards.greenhouse.io/deepmind/jobs/… Research Scientists: boards.greenhouse.io/deepmind/jobs/…

We're hiring for our Google DeepMind AGI Safety & Alignment and Gemini Safety teams. Locations: London, NYC, Mountain View, SF. Join us to help build safe AGI. Research Engineer boards.greenhouse.io/deepmind/jobs/…… Research Scientist boards.greenhouse.io/deepmind/jobs/…

Now remember kids, never forget to split your keys.

grugbrain.dev grug no able see complexity demon, but grug sense presence in code base, very dangerous

Had a great conversation with Daniel about our MONA paper. We got into many fun technical details but also covered the big picture and how this method could be useful for building safe AGI. Thanks for having me on!

1/8: The Emergent Misalignment paper showed LLMs trained on insecure code then want to enslave humanity...?! We're releasing two papers exploring why! We: - Open source small clean EM models - Show EM is driven by a single evil vector - Show EM has a mechanistic phase transition

Huge repository of information about OpenAI and Altman just dropped — 'The OpenAI Files'. There's so much crazy shit in there. Here's what Claude highlighted to me: 1. Altman listed himself as Y Combinator chairman in SEC filings for years — a total fabrication (?!): "To