Construct · 1 fields · 1 citations

representation engineering: 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.

AI safety

a top-down approach to transparency that reads and controls high-level concepts such as honesty through population-level representations inside a model.

In AI safety, representation engineering refers to a top-down approach to transparency that reads and controls high-level concepts such as honesty through population-level representations inside a model. This meaning comes from Zou (2023) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how representation engineering 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

model3 fields · 3 citationsjingle · one word, three constructs representation7 fields · 9 citationsjingle · one name, six constructs safety2 fields · 2 citationsjingle · one word, two constructs

References

Zou, A., Phan, L., Chen, S., Campbell, J., Guo, P., Ren, R., Pan, A., Yin, X., Mazeika, M., Dombrowski, A., Goel, S., Li, N., Byun, M. J., Wang, Z., Mallen, A., Basart, S., Koyejo, S., Song, D., Fredrikson, M., Kolter, J. Z., & Hendrycks, D. (2023). Representation Engineering: A Top-Down Approach to AI Transparency. arXiv. https://doi.org/10.48550/arxiv.2310.01405

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