LESSWRONGTags
LW

Redwood Research

EditHistorySubscribe

Help improve this page

EditHistorySubscribe

Help improve this page

Redwood Research

Contributors

Posts tagged Redwood Research

8

194Causal Scrubbing: a method for rigorously testing interpretability hypotheses [Redwood Research]

LawrenceC, Adrià Garriga-alonso, Nicholas Goldowsky-Dill, ryan_greenblatt, jenny, Ansh Radhakrishnan, Buck, Nate Thomas

1y

29

5

134Apply to the Redwood Research Mechanistic Interpretability Experiment (REMIX), a research program in Berkeley

maxnadeau, Xander Davies, Buck, Nate Thomas

1y

14

4

138Takeaways from our robust injury classifier project [Redwood Research]

1y

11

4

80Benchmarks for Detecting Measurement Tampering [Redwood Research]

ryan_greenblatt, Fabien Roger

3mo

10

3

145Redwood Research’s current project

2y

29

3

48Redwood's Technique-Focused Epistemic Strategy

2y

1

3

16AXRP Episode 17 - Training for Very High Reliability with Daniel Ziegler

1y

0

2

142High-stakes alignment via adversarial training [Redwood Research report]

dmz, LawrenceC, Nate Thomas

2y

29

2

114Why I'm excited about Redwood Research's current project

paulfchristiano

2y

6

2

40Some common confusion about induction heads

Alexandre Variengien

8mo

4

2

13[Linkpost] Critiques of Redwood Research

8mo

2

1

96Some Lessons Learned from Studying Indirect Object Identification in GPT-2 small

KevinRoWang, Alexandre Variengien, Arthur Conmy, Buck, jsteinhardt

1y

7

1

87Practical Pitfalls of Causal Scrubbing

Jérémy Scheurer, Phil3, tony, jacquesthibs, David Lindner

8mo

17

1

56We're Redwood Research, we do applied alignment research, AMA

2y

2

1

50Help out Redwood Research’s interpretability team by finding heuristics implemented by GPT-2 small

Haoxing Du, Buck

1y

11