Construct · 1 fields · 1 citations

activation steering: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Explainable artificial intelligence

changing a language model's behavior at inference time by adding a direction to its internal activations rather than changing weights.

In explainable artificial intelligence, activation steering refers to changing a language model's behavior at inference time by adding a direction to its internal activations rather than changing weights. This meaning comes from Turner (2023) in arXiv.[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how activation steering sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

activation4 fields · 4 citationsjingle · one word, four constructs explainable artificial intelligence1 fields · 1 citationsanchor · a standalone construct inference3 fields · 5 citationsjingle · one word, three constructs

References

Turner, A. M., Thiergart, L., Leech, G., Udell, D., Vazquez, J. J., Mini, U., & MacDiarmid, M. (2023). Steering Language Models With Activation Engineering. arXiv. https://doi.org/10.48550/arxiv.2308.10248

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct