Steering interpretable language models with concept algebra
guidelabs.ai
guidelabs.ai
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.
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
If you have joined our waitlist, we will notify you as soon as it is available.
We haven’t published the concept dictionary yet.
We plan to release it in soon with other important artifacts.
In practice, you can treat concepts as soft/hard constraints to bias the agent toward: (1) calling tools only when needed, (2) selecting the right tool/function, or (3) using the correct argument schema.