The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Levy. EMNLP, 2021.
☆103Sep 5, 2021Updated 5 years ago
Alternatives and similar repositories for ff-layers
Users that are interested in ff-layers are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆68May 18, 2023Updated 3 years ago
- ☆58Jun 15, 2023Updated 3 years ago
- ☆16Jul 10, 2023Updated 3 years ago
- The official code of LM-Debugger, an interactive tool for inspection and intervention in transformer-based language models.☆185May 13, 2022Updated 4 years ago
- Locating and editing factual associations in GPT (NeurIPS 2022)☆786Apr 20, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…☆62May 9, 2023Updated 3 years ago
- ☆14Apr 27, 2022Updated 4 years ago
- ☆14Feb 24, 2025Updated last year
- ☆29Apr 30, 2024Updated 2 years ago
- Tools for understanding how transformer predictions are built layer-by-layer☆619Aug 7, 2025Updated last year
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions☆125Sep 12, 2024Updated 2 years ago
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆566Jan 31, 2024Updated 2 years ago
- ☆45Nov 17, 2024Updated last year
- ☆16May 14, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆300Oct 1, 2024Updated 2 years ago
- A library for finding knowledge neurons in pretrained transformer models.☆160Feb 13, 2022Updated 4 years ago
- This is official version of KGQAGen framework. It interactively generates challenging KGQA instances from seed Wikidata entities using an…☆11May 16, 2025Updated last year
- ☆292Mar 2, 2024Updated 2 years ago
- PAIR.withgoogle.com and friend's work on interpretability methods☆239Jun 22, 2026Updated 4 months ago
- Code and test data for "On Measuring Bias in Sentence Encoders", to appear at NAACL 2019.☆58May 23, 2021Updated 5 years ago
- This repository contains the code for "Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP".☆89Aug 20, 2021Updated 5 years ago
- Dataset for Unified Editing, EMNLP 2023. This is a model editing dataset where edits are natural language phrases.☆24Sep 4, 2024Updated 2 years ago
- ☆12Jun 5, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Mechanistic Interpretability for Transformer Models☆55Jun 1, 2022Updated 4 years ago
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Oct 7, 2024Updated 2 years ago
- Redwood Research's transformer interpretability tools☆15Updated this week
- ☆131Aug 18, 2022Updated 4 years ago
- ☆11Dec 23, 2021Updated 4 years ago
- Train transformers on synthetic graph search problems to measure their scaling behavior and to do mechanistic analysis.☆10Oct 22, 2025Updated last year
- Sparse probing paper full code.☆68Dec 17, 2023Updated 2 years ago
- ☆18Jun 19, 2023Updated 3 years ago
- Python code for the "Jump to Conclusions" paper☆14Apr 24, 2023Updated 3 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆176Jul 24, 2024Updated 2 years ago
- [ICLR 2022] Code for paper "Exploring Extreme Parameter Compression for Pre-trained Language Models"(https://arxiv.org/abs/2205.10036)☆22May 24, 2023Updated 3 years ago
- ☆149Aug 4, 2024Updated 2 years ago
- The official code of TACL 2021, "Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies".☆88Oct 31, 2022Updated 3 years ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,134Updated this week
- [ACL 2024] Unveiling Linguistic Regions in Large Language Models☆34Jun 9, 2024Updated 2 years ago
- Neural Unification for Logic Reasoning over Language☆22Nov 15, 2021Updated 4 years ago