Alexandre Variengien

Message

835

The case for training frontier AIs on Sumerian-only corpus

> Let your every day be full of joy, love the child that holds your hand, let your wife delight in your embrace, for these alone are the concerns of humanity.[1] > > — Epic of Gilgamesh - Tablet X Say we want to train a scientist AI to help...

Jan 15, 2024143

Input Swap Graphs: Discovering the role of neural network components at scale

This post was written as part of the work done at Conjecture. You can try input swap graphs in a collab notebook or explore the library to replicate the results. Thanks to Beren Millidge and Eric Winsor for useful discussions throughout this project. Thanks to Beren for feedback on a...

May 12, 202392

Some Lessons Learned from Studying Indirect Object Identification in GPT-2 small

To learn more about this work, check out the paper. We assume general familiarity with transformer circuits. Intro: There isn’t much interpretability work that explains end-to-end how a model is able to do some task (except for toy models). In this work, we make progress towards this goal by understanding...

Oct 28, 2022101

AI ALIGNMENT FORUM
AF

AI ALIGNMENT FORUM
AF

Alexandre Variengien

Alexandre Variengien

Alexandre Variengien

Alexandre Variengien

The case for training frontier AIs on Sumerian-only corpus

Input Swap Graphs: Discovering the role of neural network components at scale

Some Lessons Learned from Studying Indirect Object Identification in GPT-2 small

The case for training frontier AIs on Sumerian-only corpus

Input Swap Graphs: Discovering the role of neural network components at scale

Some Lessons Learned from Studying Indirect Object Identification in GPT-2 small