Explore >> Select a destination

You are here

 goodfire.ai
Goodfire | AI Interpretability
| | eigenfoo.xyz
Autoregressive Models in Deep Learning - A Brief Survey | George Ho
9.9 parsecs away

Travel
| | My current project involves working with deep autoregressive models: a class of remarkable neural networks that aren't usually seen on a first pass through deep learning. These notes are a quick write-up of my reading and research: I assume basic familiarity with deep learning, and aim to highlight general trends and similarities across autoregressive models, instead of commenting on individual architectures. tldr: Deep autoregressive models are sequence models, yet feed-forward (i.e. not recurrent); generative models, yet supervised. They are a compelling alternative to RNNs for sequential data, and GANs for generation tasks.
| | deepmind.google
Gemma Scope: helping the safety community shed light on the inner workings of language models - Google DeepMind
9.9 parsecs away

Travel
| | Announcing a comprehensive, open suite of sparse autoencoders for language model interpretability.
| | transformer-circuits.pub
Circuit Tracing: Revealing Computational Graphs in Language Models
10.6 parsecs away

Travel
| | We describe an approach to tracing the "step-by-step" computation involved when a model responds to a single prompt.
| | blog.c0nrad.io
SWU Card Reader Neural Net P1
63.5 parsecs away

Travel
|