EleutherAI / bergsonLinks
Mapping out the "memory" of neural nets with data attribution
☆39Updated this week
Alternatives and similar repositories for bergson
Users that are interested in bergson are comparing it to the libraries listed below
Sorting:
- Efficiently computing & storing token n-grams from large corpora☆26Updated last year
- Attribution-based Parameter Decomposition☆33Updated 7 months ago
- A toolkit implementing advanced methods to transfer models and model knowledge across tokenizers.☆62Updated 7 months ago
- An introduction to LLM Sampling☆79Updated last year
- ☆152Updated 5 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Updated last year
- Supercharge huggingface transformers with model parallelism.☆78Updated 6 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Updated 9 months ago
- A collection of lightweight interpretability scripts to understand how LLMs think☆89Updated 2 weeks ago
- Flexible library for merging large language models (LLMs) via evolutionary optimization (ACL 2025 Demo).☆98Updated 6 months ago
- ☆90Updated 7 months ago
- ☆59Updated 2 months ago
- Code for Zero-Shot Tokenizer Transfer☆142Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆238Updated last year
- ☆29Updated last year
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.☆31Updated 9 months ago
- ☆88Updated last month
- Applying SAEs for fine-grained control☆25Updated last year
- ☆96Updated 2 weeks ago
- Minimum Description Length probing for neural network representations☆20Updated last year
- code for training & evaluating Contextual Document Embedding models☆202Updated 8 months ago
- The NDIF server, which performs deep inference and serves nnsight requests remotely☆40Updated this week
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆66Updated 2 months ago
- Engine for collecting, uploading, and downloading model activations☆25Updated 10 months ago
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆75Updated 7 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆241Updated 2 weeks ago
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources☆150Updated 4 months ago
- PageRank for LLMs☆52Updated 4 months ago
- H-Net Dynamic Hierarchical Architecture☆81Updated 4 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆94Updated last year