inseq-team / inseqLinks
Interpretability for sequence generation models đ đ
â424Updated last month
Alternatives and similar repositories for inseq
Users that are interested in inseq are comparing it to the libraries listed below
Sorting:
- The official code of LM-Debugger, an interactive tool for inspection and intervention in transformer-based language models.â177Updated 3 years ago
- This repository collects all relevant resources about interpretability in LLMsâ358Updated 7 months ago
- Tools for understanding how transformer predictions are built layer-by-layerâ500Updated last year
- What's In My Big Data (WIMBD) - a toolkit for analyzing large text datasetsâ221Updated 7 months ago
- A python package for benchmarking interpretability techniques on Transformers.â213Updated 8 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).â202Updated 6 months ago
- Erasing concepts from neural representations with provable guaranteesâ228Updated 4 months ago
- Mechanistic Interpretability Visualizations using Reactâ257Updated 6 months ago
- â226Updated 8 months ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventionsâ756Updated 2 weeks ago
- â212Updated last year
- Datasets collection and preprocessings framework for NLP extreme multitask learningâ183Updated 5 months ago
- â101Updated 2 weeks ago
- Repository for research in the field of Responsible NLP at Meta.â200Updated last month
- Materials for EACL2024 tutorial: Transformer-specific Interpretabilityâ54Updated last year
- Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging FâŚâ573Updated last year
- Utilities for the HuggingFace transformers libraryâ68Updated 2 years ago
- A framework for few-shot evaluation of autoregressive language models.â104Updated 2 years ago
- PAIR.withgoogle.com and friend's work on interpretability methodsâ192Updated 2 weeks ago
- Sparsify transformers with SAEs and transcodersâ568Updated this week
- A Python library that encapsulates various methods for neuron interpretation and analysis in Deep NLP models.â102Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models âŚâ185Updated this week
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelâ530Updated 4 months ago
- Sparse Autoencoder for Mechanistic Interpretabilityâ250Updated 11 months ago
- Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"â451Updated last year
- All-in-one text de-duplicationâ688Updated 3 weeks ago
- A library for finding knowledge neurons in pretrained transformer models.â158Updated 3 years ago
- â76Updated 3 months ago
- Representation Engineering: A Top-Down Approach to AI Transparencyâ836Updated 10 months ago
- Using sparse coding to find distributed representations used by neural networks.â255Updated last year