hannamw / EAP-IG
☆13Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for EAP-IG
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆26Updated 5 months ago
- ☆106Updated last month
- A library for efficient patching and automatic circuit discovery.☆31Updated last month
- Sparse Autoencoder Training Library☆28Updated 3 weeks ago
- ☆32Updated last year
- ☆76Updated 9 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆25Updated 6 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆57Updated 2 weeks ago
- ☆71Updated 3 months ago
- Align your LM to express calibrated verbal statements of confidence in its long-form generations.☆19Updated 5 months ago
- Algebraic value editing in pretrained language models☆58Updated last year
- ☆33Updated 9 months ago
- ☆36Updated 3 months ago
- ☆49Updated last year
- ☆188Updated last month
- Implementation of PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆26Updated 2 weeks ago
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆64Updated 10 months ago
- Sparse probing paper full code.☆51Updated 11 months ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆36Updated 3 months ago
- ☆99Updated 3 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆62Updated 5 months ago
- ☆109Updated this week
- Function Vectors in Large Language Models (ICLR 2024)☆119Updated last month
- Using sparse coding to find distributed representations used by neural networks.☆188Updated last year
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆30Updated 8 months ago
- Universal Neurons in GPT2 Language Models☆27Updated 5 months ago
- ☆25Updated 4 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆33Updated last month
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆53Updated last month
- ☆31Updated last year