evandez / relations
How do transformer LMs encode relations?
☆38Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for relations
- ☆71Updated 3 months ago
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆85Updated 3 years ago
- Inspecting and Editing Knowledge Representations in Language Models☆108Updated last year
- ☆105Updated last month
- A library for efficient patching and automatic circuit discovery.☆31Updated last month
- ☆81Updated last year
- ☆98Updated 3 months ago
- ☆75Updated last month
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆48Updated this week
- Steering Llama 2 with Contrastive Activation Addition☆97Updated 5 months ago
- Sparse probing paper full code.☆51Updated 11 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆119Updated last month
- ☆188Updated last month
- ☆107Updated this week
- ☆170Updated 8 months ago
- ☆76Updated 9 months ago
- ☆94Updated 6 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆26Updated 5 months ago
- ☆44Updated this week
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆78Updated last year
- ☆72Updated 4 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆58Updated 8 months ago
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…☆55Updated last year
- Synthetic question-answering dataset to formally analyze the chain-of-thought output of large language models on a reasoning task.☆118Updated last month
- Steering vectors for transformer language models in Pytorch / Huggingface☆65Updated last month
- Algebraic value editing in pretrained language models☆57Updated last year
- Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆26Updated 3 weeks ago
- ☆39Updated last year
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆18Updated 8 months ago
- Using sparse coding to find distributed representations used by neural networks.☆184Updated last year