Papers › Representation Engineering: A Top-Down Approach to AI Transparency

Representation Engineering: A Top-Down Approach to AI Transparency

2 Oct 2023arXiv:2310.01405archive 2025-07-28

Andy Zou, Long Phan, Sarah Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Ann-Kathrin Dombrowski, Shashwat Goel, Nathaniel Li, Michael J. Byun, Zifan Wang, Alex Mallen, Steven Basart, Sanmi Koyejo, Dawn Song, Matt Fredrikson, J. Zico Kolter, Dan Hendrycks

In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience. RepE places population-level representations, rather than neurons or circuits, at the center of analysis, equipping us with novel methods for monitoring and manipulating high-level cognitive phenomena in deep neural networks (DNNs). We provide baselines and an initial analysis of RepE techniques, showing that they offer simple yet effective solutions for improving our understanding and control of large language models. We showcase how these methods can provide traction on a wide range of safety-relevant problems, including honesty, harmlessness, power-seeking, and more, demonstrating the promise of top-down transparency research. We hope that this work catalyzes further exploration of RepE and fosters advancements in the transparency and safety of AI systems.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2310.01405")

Code

Syntology Ran 4 of 10 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

andyzoujm/representation-engineering officialmentioned in papermentioned on GitHubpytorchMIT report
cma1114/activation_steering mentioned on GitHubpytorch report
kaiyuhe998/rulearn_idea mentioned on GitHub report
steering-vectors/steering-vectors mentioned on GitHubpytorchMIT report
sunblaze-ucb/political_leaning_RepE mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 4 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran
6unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from andyzoujm/representation-engineering. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

compute_loss andyzoujm/representation-engineering/lorra_finetune/src/llama2_lorra.py official repository ran MIT (permissive) · acc281fc1d7b77bc · report
get_position_ids andyzoujm/representation-engineering/lorra_finetune/src/train_val_datasets.py official repository ran fingerprinted MIT (permissive) · db75f13051c04007 · report
get_truncated_outputs andyzoujm/representation-engineering/lorra_finetune/src/train_val_datasets.py official repository ran MIT (permissive) · 1899aee66262f84f · report
prepare_inputs andyzoujm/representation-engineering/lorra_finetune/src/train_val_datasets.py official repository ran MIT (permissive) · 97aa4e637d9f5444 · report
arc_dataset andyzoujm/representation-engineering/repe_eval/tasks/arc.py official repository unverified MIT (permissive) · 18886c949c98a5c9 · report
contrast_greedy_search andyzoujm/representation-engineering/repe/rep_control_contrast_vec.py official repository unverified MIT (permissive) · 2b4c9fbd7f2a466f · report
csqa_dataset andyzoujm/representation-engineering/repe_eval/tasks/csqa.py official repository unverified MIT (permissive) · 2ef192a290c2db9a · report
forward_contrast_vector andyzoujm/representation-engineering/repe/rep_control_contrast_vec.py official repository unverified MIT (permissive) · a953412e8172dfef · report
project_onto_direction andyzoujm/representation-engineering/repe/rep_readers.py official repository unverified MIT (permissive) · 8c6b734d5c949090 · report
recenter andyzoujm/representation-engineering/repe/rep_readers.py official repository unverified MIT (permissive) · 1ceba3fc481567ab · report

Tasks

Question Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering TruthfulQA LLaMA-2-Chat-13B + Representation Control (Contrast Vector) MC1 0.54 #4 of 33 Archive leaderboard report
Question Answering TruthfulQA LLaMA-2-Chat-7B + Representation Control (Contrast Vector) MC1 0.48 #5 of 33 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections