efarrell1 / train_sparse_autoencoderLinks
Trains Sparse Autoencoders based on outputs from language models
☆11Updated last year
Alternatives and similar repositories for train_sparse_autoencoder
Users that are interested in train_sparse_autoencoder are comparing it to the libraries listed below
Sorting:
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆136Updated 4 months ago
- ☆48Updated 2 years ago
- [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆35Updated 2 months ago
- 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…☆12Updated 9 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆43Updated last year
- LoFiT: Localized Fine-tuning on LLM Representations☆42Updated 9 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆83Updated 7 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated last year
- ☆57Updated 3 months ago
- NeurIPS'24 - LLM Safety Landscape☆30Updated 8 months ago
- [ICLR 2025] General-purpose activation steering library☆114Updated last month
- Algebraic value editing in pretrained language models☆66Updated last year
- ☆56Updated 2 years ago
- Function Vectors in Large Language Models (ICLR 2024)☆181Updated 6 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆40Updated 11 months ago
- ☆63Updated 7 months ago
- ☆37Updated 10 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆116Updated 8 months ago
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆60Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆126Updated 8 months ago
- ☆131Updated last week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated last year
- [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors☆81Updated 10 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆66Updated 11 months ago
- ☆181Updated 11 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆98Updated 2 years ago
- Steering Llama 2 with Contrastive Activation Addition☆191Updated last year
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆61Updated last year
- ☆58Updated 2 years ago
- ☆46Updated 8 months ago