# andyzoujm/representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

Repository: https://github.com/andyzoujm/representation-engineering
Canonical: https://ross.abutalabs.com/products/representation-engineering
Homepage: https://www.ai-transparency.org/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2024-08-14T02:04:16+00:00

## Health v2 (maintenance only)
Score: 18/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 76
- inputs: {"age_days": 1072, "days_push": 750, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1024, forks 132 (observed 2026-08-28T04:03:16.346222+00:00)

## What it is
Official library for Representation Engineering (RepE), a top-down approach to AI transparency that monitors and manipulates population-level representations in large language models. It provides RepReading and RepControl pipelines registered as Hugging Face transformers pipeline tasks.

## Use cases
- monitor honesty and truthfulness of llm internal representations
- steer llm behavior via representation control vectors
- study memorization and power-seeking tendencies in language models
- run interpretability research on large language models
- detect safety-relevant cognitive states in neural networks

## When to choose
- you want to analyze or control LLM internal representations using Hugging Face models
- you are doing AI transparency or safety research based on the RepE paper

## When to avoid
- you need production LLM serving or inference optimization
- you work with non-Hugging Face model ecosystems

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, llm-inference, monitoring, testing
- domain: large-language-models, artificial-intelligence, machine-learning
- platform: python
- tags: interpretability, ai-safety, representation-engineering, llm-steering, huggingface, research

## Member repositories
- andyzoujm/representation-engineering (main) score 18

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:16.346222+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:08:07.646451+00:00, confidence not recorded.
  - readme: https://github.com/andyzoujm/representation-engineering (fetched 2026-08-28T04:03:16.346222+00:00, sha 5afe83678ab5)
  - homepage: https://www.ai-transparency.org/ (fetched 2026-08-29T13:08:38.781633+00:00, sha c243a6c291cb)
- Data as of 2026-08-30T08:39:29.467469+00:00.