publication
Representation Engineering: A Top-Down Approach to AI Transparency
Metadata
| Source Table | publications |
| Source ID | Gti3A1NyT6 |
| Description | Andy Zou, Long Phan, Sarah Chen et al., 2023-10 |
| Source URL | arxiv.org/abs/2310.01405 |
| Parent | Center for AI Safety (CAIS) |
| Children | — |
| Created | Mar 23, 2026, 2:46 PM |
| Updated | Mar 23, 2026, 2:46 PM |
| Synced | Mar 23, 2026, 2:46 PM |
Record Data
id | Gti3A1NyT6 |
entityId | Center for AI Safety (CAIS)(organization) |
entityDisplayName | — |
resourceId | — |
title | Representation Engineering: A Top-Down Approach to AI Transparency |
authors | Andy Zou, Long Phan, Sarah Chen et al. |
url | arxiv.org/abs/2310.01405 |
venue | — |
publishedDate | 2023-10 |
publicationType | paper |
citationCount | — |
isFlagship | Yes |
abstract | — |
source | arxiv.org/abs/2310.01405 |
notes | — |
Source Check Verdicts
confirmed95% confidence
Last checked: 4/3/2026
The source text confirms all key fields in the record. The title matches exactly. The authors listed in the record (Andy Zou, Long Phan, Sarah Chen et al.) are confirmed in the source document's author list. The publication date of 2023-10 corresponds to the arXiv identifier 2310.01405 (October 2023). The URL format matches the standard arXiv URL structure for this paper. The publication type as 'paper' is appropriate for an arXiv preprint. All verifiable claims are accurate.
Debug info
Thing ID: Gti3A1NyT6
Source Table: publications
Source ID: Gti3A1NyT6