CLT Features Support Manifold Steering, but Hold Only Partial Steering Signal

·LessWrong··

tl;dr I continue work to extend the Goodfire lab's cyclical manifold methods to Anthropic's pre-trained CLT feature space on Gemma-2-2B. I find that manifold steering produces the expected cyclical transition between days of the week in both activation space and CLT feature space, but that CLT features provide a weaker steering signal, suggesting that the MLP sublayers in which they originate only hold a portion of the full day-of-the-week signal. Colab notebook implementation can be found here....

Read full article →

Related Articles

NASA’s Mars Sample Return mission is dead
Muhammad523 · Hacker News · 3h ago
What happened to the Snowden archive
EXHades · Hacker News · 1d ago
Samsung is expected to more than double output of its HBM4 and HBM4E DRAM
giuliomagnifico · Hacker News · 1d ago
Ask HN: Is it impossible to disable Siri on macOS 27?
semidror · Hacker News · 10h ago
Qwen Image 2.1
jmillikin · Hacker News · 1d ago