mattneary / attentionLinks
visualizing attention for LLM users
☆236Updated 11 months ago
Alternatives and similar repositories for attention
Users that are interested in attention are comparing it to the libraries listed below
Sorting:
- Evaluating LLMs with fewer examples☆169Updated last year
- Extract full next-token probabilities via language model APIs☆248Updated last year
- ☆297Updated 2 years ago
- What's In My Big Data (WIMBD) - a toolkit for analyzing large text datasets☆224Updated last year
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆532Updated last year
- A package to generate summaries of long-form text and evaluate the coherence of these summaries. Official package for our ICLR 2024 paper…☆128Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆549Updated 3 months ago
- ☆257Updated 8 months ago
- Code accompanying "How I learned to start worrying about prompt formatting".☆112Updated 5 months ago
- Controlled Text Generation via Language Model Arithmetic☆223Updated last year
- [EMNLP 2023] Adapting Language Models to Compress Long Contexts☆319Updated last year
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆193Updated 9 months ago
- TART: A plug-and-play Transformer module for task-agnostic reasoning☆201Updated 2 years ago
- Fast & more realistic evaluation of chat language models. Includes leaderboard.☆189Updated last year
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆250Updated 9 months ago
- ☆556Updated last year
- DSIR large-scale data selection framework for language model training☆266Updated last year
- ☆313Updated last year
- ☆157Updated last year
- PASTA: Post-hoc Attention Steering for LLMs☆129Updated last year
- awesome synthetic (text) datasets☆310Updated 2 weeks ago
- Code for "SemDeDup", a simple method for identifying and removing semantic duplicates from a dataset (data pairs which are semantically s…☆147Updated 2 years ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆130Updated 9 months ago
- ☆199Updated 7 months ago
- Scaling Data-Constrained Language Models☆342Updated 5 months ago
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆560Updated 10 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆231Updated 11 months ago
- Reverse Instructions to generate instruction tuning data with corpus examples☆216Updated last year
- RuLES: a benchmark for evaluating rule-following in language models☆240Updated 9 months ago
- ☆283Updated last year