EleutherAI (@aieleuther) 's Twitter Profile
EleutherAI

@aieleuther

A non-profit research lab focused on interpretability, alignment, and ethics of artificial intelligence.

Creators of GPT-J, GPT-NeoX, Pythia, and VQGAN-CLIP

ID: 1561918448766173185

linkhttp://www.eleuther.ai calendar_today23-08-2022 03:29:21

690 Tweet

20,20K Followers

77 Following

Kyle O'Brien (@kyledevinobrien) 's Twitter Profile Photo

How do popular LM interventions like editing, compression, and unlearning interact? We study to what degree popular interventions are composable — a crucial requirement for their practical application relevant to factuality, safety, and efficiency. 🧵 arxiv.org/pdf/2407.06483

How do popular LM interventions like editing, compression, and unlearning interact? We study to what degree popular interventions are composable — a crucial requirement for their practical application relevant to factuality, safety, and efficiency. 🧵

 arxiv.org/pdf/2407.06483
Aviya Skowron (@aviskowron) 's Twitter Profile Photo

Tomorrow 11 am EDT / 8 am PDT I'll be discussing openness across the AI stack + building open datasets and the tech and policy challenges that come with it, based on two recent Mozilla workshops. Sign up here: eventbrite.co.uk/e/openuk-resea…

Aviya Skowron (@aviskowron) 's Twitter Profile Photo

Mozilla The dataset work stems from the Dataset Convening, co-hosted by EleutherAI. Here's a blog post summarizing the event: blog.mozilla.org/en/mozilla/dat…

Curt Tigges (@curttigges) 's Twitter Profile Photo

Circuit analysis is a common tool in mechanistic interpretability for understanding model behaviors when executing certain tasks. But how well do these findings generalize throughout model training or to models of different sizes?

Circuit analysis is a common tool in mechanistic interpretability for understanding model behaviors when executing certain tasks. But how well do these findings generalize throughout model training or to models of different sizes?
EleutherAI (@aieleuther) 's Twitter Profile Photo

As models become larger and more unwieldy, auto-interp methods have becoming increasingly important. We are excited to be releasing the most comprehensive auto interp library to enable wider research on this topic. github.com/EleutherAI/sae…

EleutherAI (@aieleuther) 's Twitter Profile Photo

We were very happy with the reception to our researchers Lintang Sutawika and Hailey Schoelkopf 's ICML tutorial, "Challenges in LM Evaluation", this past week! For all those who requested it, the slides are now available at lm-evaluation-challenges.github.io . Enjoy!

RWKV (@rwkv_ai) 's Twitter Profile Photo

The RWKV v6 Finch lines of models are here Scaling from 1.6B all the way to 14B Pushing the boundary for an Attention-free transformer, and Multi-lingual models. Cleanly licensedm Apache 2, under The Linux Foundation Find out more from the writeup here: blog.rwkv.com/p/rwkv-v6-finc…