Logan Riggs

Karma: 3,666

Temporarily Losing My Ego

Logan Riggs28 Oct 2025 16:41 UTC

21 points

3 comments3 min readLW link

Hospitalization: A Review

Logan Riggs9 Oct 2025 14:36 UTC

354 points

19 comments9 min readLW link

Replacing RL w/ Parameter-based Evolutionary Strategies

Logan Riggs8 Oct 2025 1:02 UTC

63 points

5 comments3 min readLW link

Telling the Difference Between Memories & Logical Guesses

Logan Riggs7 Oct 2025 5:46 UTC

28 points

3 comments4 min readLW link

Making Your Pain Worse can Get You What You Want

Logan Riggs5 Oct 2025 0:19 UTC

86 points

5 comments3 min readLW link

How to Feel More Alive

Logan Riggs2 Oct 2025 15:45 UTC

49 points

2 comments4 min readLW link

Looking for feature absorption automatically

Theodore Ehrenborg, Logan Riggs and Cleo Nardo

12 Aug 2025 20:46 UTC

16 points

0 comments6 min readLW link

Veo-2 Can Produce Realistic Ads

Logan Riggs21 Jan 2025 19:13 UTC

14 points

0 comments1 min readLW link

[Exercise] Four Examples of Noticing Confusion

Logan Riggs18 Jan 2025 15:29 UTC

8 points

8 comments3 min readLW link

How do you deal w/ Super Stimuli?

Logan Riggs14 Jan 2025 15:14 UTC

112 points

25 comments3 min readLW link

When AI 10x’s AI R&D, What Do We Do?

Logan Riggs21 Dec 2024 23:56 UTC

72 points

17 comments4 min readLW link

Logan Riggs’s Shortform

Logan Riggs4 Dec 2024 14:52 UTC

7 points

20 comments1 min readLW link

Book a Time to Chat about Interp Research

Logan Riggs3 Dec 2024 17:27 UTC

47 points

3 comments1 min readLW link

Evaluating Sparse Autoencoders with Board Game Models

Adam Karvonen, Sam Marks, Can, Benjamin Wright, Jannik Brinkmann, Logan Riggs and Rico Angell

2 Aug 2024 19:50 UTC

38 points

1 comment9 min readLW link

Interpreting Preference Models w/ Sparse Autoencoders

Logan Riggs and Jannik Brinkmann

1 Jul 2024 21:35 UTC

75 points

12 comments9 min readLW link

Was Releasing Claude-3 Net-Negative?

Logan Riggs27 Mar 2024 17:41 UTC

52 points

5 comments4 min readLW link

Improving SAE’s by Sqrt()-ing L1 & Removing Lowest Activating Features

Logan Riggs and Jannik Brinkmann

15 Mar 2024 16:30 UTC

26 points

5 comments4 min readLW link

Finding Sparse Linear Connections between Features in LLMs

Logan Riggs, Sam Mitchell and Adam Kaufman

9 Dec 2023 2:27 UTC

70 points

5 comments10 min readLW link

Sparse Autoencoders: Future Work

Logan Riggs and Aidan Ewart

21 Sep 2023 15:30 UTC

35 points

5 comments6 min readLW link

Sparse Autoencoders Find Highly Interpretable Directions in Language Models

Logan Riggs, Hoagy, Aidan Ewart and Robert_AIZI

21 Sep 2023 15:30 UTC

159 points

8 comments5 min readLW link