openai / automated-interpretabilityLinks
☆1,020Updated last year
Alternatives and similar repositories for automated-interpretability
Users that are interested in automated-interpretability are comparing it to the libraries listed below
Sorting:
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,001Updated 2 years ago
- [NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.☆763Updated 7 months ago
- Dromedary: towards helpful, ethical and reliable LLMs.☆1,146Updated last month
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,747Updated last year
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆812Updated 11 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,113Updated last year
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆527Updated 4 months ago
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆494Updated last year
- Locating and editing factual associations in GPT (NeurIPS 2022)☆636Updated last year
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them☆495Updated 11 months ago
- ☆755Updated 11 months ago
- OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.☆561Updated last year
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,524Updated this week
- ☆1,521Updated last month
- A prize for finding tasks that cause large language models to show inverse scaling☆611Updated last year
- [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition☆637Updated 10 months ago
- TruthfulQA: Measuring How Models Imitate Human Falsehoods☆738Updated 4 months ago
- Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).☆769Updated last year
- MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.☆930Updated 2 months ago
- ☆1,032Updated 2 years ago
- Representation Engineering: A Top-Down Approach to AI Transparency☆832Updated 9 months ago
- PaL: Program-Aided Language Models (ICML 2023)☆500Updated last year
- Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"☆1,060Updated last year
- LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.☆699Updated 8 months ago
- LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions☆821Updated 2 years ago
- ☆534Updated last year
- LOMO: LOw-Memory Optimization☆986Updated 11 months ago
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆547Updated last year
- Expanding natural instructions☆998Updated last year
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆643Updated 5 months ago