cd/entity/Lindsey et al.· home› entities› Lindsey et al.
grep -l @lindsey et al. /news/*.json | wc -l → 2

Lindsey et al.

mentions 2 type Person feed RSS

// recent coverage 2 mentions

04:14
2026-07-27
lesswrong.com
machine-learning

You don't need error nodes, you need better features

A new training method called replacement-aware training produces sparse auto-encoders (SAEs) that retain language capabilities when used in a full replacement model of Gemma-2-2B, unlike standard SAEs…

05:58
2026-05-30
lesswrong.com
ai-safety

Belief manifolds, and how to steer along them

A BlueDot Technical AI Safety Project researcher reproduced a study from Goodfire demonstrating that language model representations form curved geometric manifolds, not simple linear directions. The w…

// co-occurs with top 8 entities
BlueDot Technical AI Safety Project 1 Goodfire 1 Sarfati et al. 1 Francis Bacon 1 Chen et al. 1 Evan Lloyd 1 Gemma-2-2B 1 Gemma Team 1
// topics top 6 topics
machine learning 2 large language models 2 ai research 2 ai safety 1 neural networks 1 ai tools 1