[NeurIPS 2025 MechInterp Workshop - Spotlight] Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching"
☆27Nov 3, 2025Updated 3 months ago
Alternatives and similar repositories for RelP
Users that are interested in RelP are comparing it to the libraries listed below
Sorting:
- 🪝PISCES - Precise In-Parameter Suppression for Concept EraSure in Large Language Models☆12May 30, 2025Updated 9 months ago
- Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/☆26Mar 10, 2025Updated 11 months ago
- Localization of Knowledge in Text-to-Image Models☆12Oct 8, 2024Updated last year
- ☆17Aug 30, 2025Updated 6 months ago
- ☆19Sep 16, 2025Updated 5 months ago
- ☆15Jun 4, 2025Updated 8 months ago
- Concept Relevance Propagation for Localization Models, accepted at SAIAD workshop at CVPR 2023.☆15Jan 16, 2024Updated 2 years ago
- Find informative examples to efficiently (human)-evaluate NLG models.☆18Updated this week
- Attribute statements generated by LLMs to preceding tokens using attention weights.☆22Apr 22, 2025Updated 10 months ago
- [NeurIPS 2024] Official implementation of the paper "MambaLRP: Explaining Selective State Space Sequence Models" 🐍☆45Nov 6, 2024Updated last year
- DecompX: Explaining Transformers Decisions by Propagating Token Decomposition [ACL 2023]☆19Jul 3, 2025Updated 7 months ago
- ☆18Oct 6, 2022Updated 3 years ago
- Code for Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals.☆18Apr 25, 2021Updated 4 years ago
- Saliency Cards are transparency documentation for saliency methods. Learn about new saliency methods or document your own!☆19Jun 9, 2023Updated 2 years ago
- Landing page for MIB: A Mechanistic Interpretability Benchmark☆24Aug 15, 2025Updated 6 months ago
- [NAACL 2022] GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers☆21May 16, 2023Updated 2 years ago
- Mapping out the "memory" of neural nets with data attribution☆45Updated this week
- Data and code accompanying the paper "As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive…☆22Apr 13, 2023Updated 2 years ago
- Pruning CNN using CNN with toy example☆22Jun 21, 2021Updated 4 years ago
- Prototyping about eXplainable Artificial Inteligence (XAI)☆26Jan 5, 2023Updated 3 years ago
- ☆13Oct 5, 2025Updated 4 months ago
- This repo contains code to reproduce some of the results presented in the paper "SentenceMIM: A Latent Variable Language Model"☆28Jun 22, 2022Updated 3 years ago
- Measuring the Mixing of Contextual Information in the Transformer☆34May 27, 2023Updated 2 years ago
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆241Jan 30, 2026Updated last month
- [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆39Aug 20, 2025Updated 6 months ago
- A toolkit for quantitative evaluation of data attribution methods.☆56Jul 14, 2025Updated 7 months ago
- A framework for evaluating Machine Translation models.☆12May 26, 2025Updated 9 months ago
- Rationales for Sequential Predictions☆40Mar 10, 2022Updated 3 years ago
- ☆13Jul 26, 2023Updated 2 years ago
- Code for the NAACL 2024 HCI+NLP Workshop paper "LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tool…☆13Mar 24, 2024Updated last year
- Brain Interpreter and Visualizer Online.☆10Sep 1, 2016Updated 9 years ago
- For further understanding the wide array of emotions embedded in human speech, we are introducing an emotional speech corpus. In contrast…☆11Oct 29, 2018Updated 7 years ago
- Codes for "Benchmarking the Generation of Fact Checking Explanations"☆10Aug 16, 2024Updated last year
- Reasoning-based Evaluation and Ranking of Translations.☆19Jul 18, 2025Updated 7 months ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆43Feb 12, 2025Updated last year
- HealthFC: Verifying Health Claims with Evidence-Based Medical Fact-Checking☆12Apr 11, 2025Updated 10 months ago
- VertMetric: An abstractive summarization evaluation package. VERT stands for Versatile Evaluation of Reduced Texts.☆11Dec 20, 2018Updated 7 years ago
- ☆10Mar 19, 2024Updated last year
- ☆10Dec 17, 2020Updated 5 years ago