Aaquib111 / edge-attribution-patchingLinks
Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
☆35Updated last year
Alternatives and similar repositories for edge-attribution-patching
Users that are interested in edge-attribution-patching are comparing it to the libraries listed below
Sorting:
- A library for efficient patching and automatic circuit discovery.☆66Updated 2 months ago
- ☆35Updated last month
- ☆119Updated 10 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- Sparse probing paper full code.☆58Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆47Updated 8 months ago
- ☆84Updated 10 months ago
- ☆226Updated 8 months ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆27Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- ☆101Updated 2 weeks ago
- Sparse Autoencoder Training Library☆52Updated last month
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆27Updated last year
- ☆95Updated 4 months ago
- ☆129Updated 7 months ago
- ☆173Updated 2 months ago
- ☆76Updated 3 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆106Updated 4 months ago
- ☆44Updated 7 months ago
- Steering Llama 2 with Contrastive Activation Addition☆158Updated last year
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆11Updated 4 months ago
- ☆34Updated 5 months ago
- How do transformer LMs encode relations?☆48Updated last year
- ☆121Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆59Updated 6 months ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 4 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- Attribution-based Parameter Decomposition☆25Updated last week
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 3 months ago
- ☆67Updated 2 years ago