Settings

Theme

Steering interpretable language models with concept algebra

guidelabs.ai

29 points by luulinh90s 21 hours ago · 2 comments

Reader

giang_at_glai 15 hours ago

Author here.

This post shows “concept algebra” on language model: inject, suppress, and compose human-understandable concepts at inference time (no retraining, no prompt engineering).

There’s an interactive demo on the post.

Would love feedback on: (1) what steering tasks you’d benchmark, (2) failure cases you’d want to see, (3) whether this kind of compositional control is useful in real products.

Related: https://news.ycombinator.com/item?id=47131225

  • anon291 36 minutes ago

    I would personally like some quantification of how good this is compared to just replacing the system prompt of an off the shelf 8B parameter language model.

    The suppression bit is very powerful. I would like to see a quantification of how often a steered 'normal' language model will mention things you asked it to suppress vs how often this one does

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection