fdalvi / NeuroX
A Python library that encapsulates various methods for neuron interpretation and analysis in Deep NLP models.
☆102Updated last year
Alternatives and similar repositories for NeuroX:
Users that are interested in NeuroX are comparing it to the libraries listed below
- Materials for EACL2024 tutorial: Transformer-specific Interpretability☆50Updated last year
- ☆96Updated 2 years ago
- diagNNose is a Python library that facilitates a broad set of tools for analysing hidden activations of neural models.☆81Updated last year
- Minimum Bayes Risk Decoding for Hugging Face Transformers☆57Updated 10 months ago
- Materials for "Prompting is not a substitute for probability measurements in large language models" (EMNLP 2023)☆22Updated last year
- Code repository for the paper "Mission: Impossible Language Models."☆52Updated last week
- Source code for CoNLL 2021 paper by Huebner et al. 2021☆18Updated last year
- How do transformer LMs encode relations?☆47Updated last year
- A curated list of research papers and resources on Cultural LLM.☆41Updated 6 months ago
- ☆89Updated 2 years ago
- A curated list of awesome datasets with human label variation (un-aggregated labels) in Natural Language Processing and Computer Vision, …☆82Updated last year
- This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”☆85Updated 2 years ago
- Utilities for the HuggingFace transformers library☆67Updated 2 years ago
- Measuring the Mixing of Contextual Information in the Transformer☆29Updated last year
- A library for finding knowledge neurons in pretrained transformer models.☆155Updated 3 years ago
- Utility for behavioral and representational analyses of Language Models☆136Updated this week
- ☆34Updated 10 months ago
- Simple-to-use scoring function for arbitrarily tokenized texts.☆39Updated 2 months ago
- ☆39Updated 3 years ago
- Code for paper "Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs"☆28Updated 2 years ago
- To analyze and remove gender bias in coreference resolution systems☆77Updated 3 years ago
- The geometry of multilingual language model representations (EMNLP 2022).☆20Updated 2 years ago
- Highlight errors in a bib file: missing URLs, capitalization protection, etc☆27Updated 11 months ago
- Evaluation pipeline for the BabyLM Challenge 2023.☆75Updated last year
- ☆58Updated 4 years ago
- ☆31Updated last year
- ☆106Updated 11 months ago
- A Python Commonsense Knowledge Inference Toolkit☆64Updated last year
- ☆34Updated 6 months ago
- ☆39Updated last year