rhubarbwu / linguistic-collapse
Codebase for Linguistic Collapse: Neural Collapse in (Large) Language Models [NeurIPS 2024] [arXiv:2405.17767]
☆11Updated last week
Alternatives and similar repositories for linguistic-collapse:
Users that are interested in linguistic-collapse are comparing it to the libraries listed below
- ☆66Updated 3 years ago
- ☆91Updated 2 months ago
- ☆27Updated last month
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆63Updated 6 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated last month
- [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors☆75Updated 4 months ago
- Code for "Automatic Circuit Finding and Faithfulness"☆10Updated 9 months ago
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆71Updated 2 weeks ago
- ☆93Updated last year
- ☆87Updated 9 months ago
- ☆33Updated 4 months ago
- General-purpose activation steering library☆61Updated 3 months ago
- ☆30Updated 9 months ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆101Updated last year
- Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…☆16Updated 5 months ago
- ☆40Updated last year
- Sparse probing paper full code.☆55Updated last year
- LLM finetuning in resource-constrained environments.☆47Updated 10 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…☆11Updated 3 months ago
- AI Logging for Interpretability and Explainability🔬☆111Updated 10 months ago
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]☆17Updated 11 months ago
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆145Updated 8 months ago
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆90Updated 3 years ago
- ☆161Updated 2 weeks ago
- ☆226Updated 11 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆30Updated 10 months ago
- ☆49Updated last year
- ☆27Updated last week
- ☆85Updated 2 weeks ago
- ☆29Updated 11 months ago