shacharKZ / VISIT-Visualizing-TransformersLinks
☆26Updated last year
Alternatives and similar repositories for VISIT-Visualizing-Transformers
Users that are interested in VISIT-Visualizing-Transformers are comparing it to the libraries listed below
Sorting:
- Sparse probing paper full code.☆62Updated last year
- ☆66Updated 2 years ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated last year
- ☆57Updated 3 months ago
- ☆108Updated 8 months ago
- [ICLR 2025] General-purpose activation steering library☆114Updated last month
- ☆18Updated 2 months ago
- Inspecting and Editing Knowledge Representations in Language Models☆119Updated 2 years ago
- ☆236Updated last year
- [ACL 2023] Knowledge Unlearning for Mitigating Privacy Risks in Language Models☆83Updated last year
- ☆98Updated 2 years ago
- ☆131Updated last week
- ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.☆149Updated 2 months ago
- Code and data for Marked Personas (ACL 2023)☆28Updated 2 years ago
- How do transformer LMs encode relations?☆55Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆191Updated last year
- ☆154Updated 2 years ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆83Updated 7 months ago
- Code and data for Koo et al's ACL 2024 paper "Benchmarking Cognitive Biases in Large Language Models as Evaluators"☆21Updated last year
- Package to compute Mauve, a similarity score between neural text and human text. Install with `pip install mauve-text`.☆298Updated last year
- ☆57Updated 2 years ago
- ☆191Updated 2 weeks ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆42Updated last year
- Repository for research in the field of Responsible NLP at Meta.☆202Updated 5 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆181Updated 6 months ago
- Materials for EACL2024 tutorial: Transformer-specific Interpretability☆60Updated last year
- ☆116Updated last year
- "Understanding Dataset Difficulty with V-Usable Information" (ICML 2022, outstanding paper)☆88Updated 2 years ago
- MEND: Fast Model Editing at Scale☆251Updated 2 years ago
- ☆248Updated last year