Alternatives and similar repositories for representation-engineering

Users that are interested in representation-engineering are comparing it to the libraries listed below

• likenneth / honest_llama
  Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
  ☆567Updated 11 months ago
• kmeng01 / rome
  Locating and editing factual associations in GPT (NeurIPS 2022)
  ☆717Updated last year
• kmeng01 / memit
  Mass-editing thousands of facts into a transformer memory (ICLR 2023)
  ☆535Updated last year
• ContextualAI / HALOs
  A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
  ☆899Updated 3 months ago
• stanfordnlp / pyvene
  Stanford NLP Python library for understanding and improving PyTorch models via interventions
  ☆853Updated 3 months ago
• openai / sparse_autoencoder
  ☆562Updated last year
• allenai / reward-bench
  RewardBench: the first evaluation tool for reward models.
  ☆683Updated last week
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆564Updated 5 months ago
• decoderesearch / SAELens
  Training Sparse Autoencoders on Language Models
  ☆1,169Updated this week
• voidism / DoLa
  Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"
  ☆533Updated last year
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆684Updated last week
• jlko / semantic_uncertainty
  Codebase for reproducing the experiments of the semantic uncertainty paper (short-phrase and sentence-length experiments).
  ☆403Updated last year
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆333Updated 7 months ago
• ruizheliUOA / Awesome-Interpretability-in-Large-Language-Models
  This repository collects all relevant resources about interpretability in LLMs
  ☆389Updated last year
• RUCAIBox / HaluEval
  This is the repository of HaluEval, a large-scale hallucination evaluation benchmark for Large Language Models.
  ☆549Updated last year
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆293Updated 2 years ago
• teacherpeterpan / self-correction-llm-papers
  This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.
  ☆563Updated last year
• srush / awesome-o1
  A bibliography and survey of the papers surrounding o1
  ☆1,214Updated last year
• yule-BUAA / MergeLM
  Codebase for Merging Language Models (ICML 2024)
  ☆862Updated last year
• EdinburghNLP / awesome-hallucination-detection
  List of papers on hallucination detection in LLMs.
  ☆1,023Updated 2 weeks ago
• ezelikman / quiet-star
  Code for Quiet-STaR
  ☆742Updated last year
• cooperleong00 / Awesome-LLM-Interpretability
  A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..
  ☆290Updated last month
• tatsu-lab / gpt_paper_assistant
  GPT4 based personalized ArXiv paper assistant bot
  ☆541Updated last year
• jxzhangjhu / Awesome-LLM-Uncertainty-Reliability-Robustness
  Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models
  ☆811Updated 8 months ago
• zjunlp / Prompt4ReasoningPapers
  [ACL 2023] Reasoning with Language Model Prompting: A Survey
  ☆994Updated 8 months ago
• glgh / awesome-llm-human-preference-datasets
  A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.
  ☆387Updated 2 years ago
• davidbau / baukit
  ☆244Updated last year
• chujiezheng / chat_templates
  Chat Templates for 🤗 HuggingFace Large Language Models
  ☆713Updated last year
• zjunlp / KnowledgeEditingPapers
  Must-read Papers on Knowledge Editing for Large Language Models.
  ☆1,212Updated 6 months ago
• declare-lab / instruct-eval
  This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.
  ☆551Updated last year