sciai-lab / Truth_is_UniversalLinks
☆25Updated 7 months ago
Alternatives and similar repositories for Truth_is_Universal
Users that are interested in Truth_is_Universal are comparing it to the libraries listed below
Sorting:
- ☆83Updated 9 months ago
- ☆44Updated last year
- General-purpose activation steering library☆75Updated 3 weeks ago
- ☆50Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆98Updated 3 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆93Updated last year
- ☆40Updated 3 months ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆67Updated 8 months ago
- AI Logging for Interpretability and Explainability🔬☆119Updated last year
- Materials for EACL2024 tutorial: Transformer-specific Interpretability☆54Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆92Updated this week
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 2 months ago
- ☆34Updated 2 weeks ago
- Code for the paper "Spectral Editing of Activations for Large Language Model Alignments"☆24Updated 5 months ago
- Steering Llama 2 with Contrastive Activation Addition☆155Updated last year
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆58Updated 6 months ago
- Conformal Language Modeling☆29Updated last year
- How do transformer LMs encode relations?☆48Updated last year
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆91Updated 3 years ago
- ☆133Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆47Updated 8 months ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 3 months ago
- The Prism Alignment Project☆76Updated last year
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆34Updated 6 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆34Updated last year
- Repository for the Bias Benchmark for QA dataset.☆116Updated last year
- ☆106Updated last year
- Sparse probing paper full code.☆56Updated last year
- A resource repository for representation engineering in large language models☆124Updated 6 months ago