Apart Research

Edited by Esben Kran, habryka, Jason Hoelscher-Obermaier last updated 18th Jul 2024

Apart Research is an AI safety research lab. They host the Apart Sprints, large-scale international events for research experimentation. This tag includes posts written by Apart researchers and content about Apart Research.

Posts tagged Apart Research

26Newsletter for Alignment Research: The ML Safety Updates

Esben Kran

3y

0

9Black Box Investigation Research Hackathon

Esben Kran, Jonas Hallgren

3y

4

143We Found An Neuron in GPT-2

Ω

Joseph Miller, Clement Neo

3y

Ω

23

38Safety timelines: How long will it take to solve alignment?

Esben Kran, JonathanRystroem, Steinthal

3y

7

33Deceptive agents can collude to hide dangerous features in SAEs

Simon Lermen, Mateusz Dziemian

1y

2

24AI Safety Ideas: A collaborative AI safety research platform

Esben Kran

3y

0

22Results from the language model hackathon

Esben Kran

3y

1

9Analysing Adversarial Attacks with Linear Probing

Ω

Yoann Poupart, Imene Kerboua, Clement Neo, Jason Hoelscher-Obermaier

1y

Ω

0

119Solving the Mechanistic Interpretability challenges: EIS VII Challenge 1

Ω

StefanHex, Marius Hobbhahn

2y

Ω

1

81Results from the interpretability hackathon

Esben Kran, Neel Nanda

3y

0

71Solving the Mechanistic Interpretability challenges: EIS VII Challenge 2

Ω

StefanHex, Marius Hobbhahn

2y

Ω

1

47Robustness of Model-Graded Evaluations and Automated Interpretability

Ω

Simon Lermen, viluon

2y

Ω

5

47How-to Transformer Mechanistic Interpretability—in 50 lines of code or less!

Ω

StefanHex

3y

Ω

5

44College technical AI safety hackathon retrospective - Georgia Tech

yix

10mo

2

34Computational Mechanics Hackathon (June 1 & 2)

Adam Shai

1y

5

LESSWRONG
LW

LESSWRONG
LW

Apart Research