liuyz0 / SuperpositionScalingLinks
☆17Updated 6 months ago
Alternatives and similar repositories for SuperpositionScaling
Users that are interested in SuperpositionScaling are comparing it to the libraries listed below
Sorting:
- Universal Neurons in GPT2 Language Models☆31Updated last year
- Sparse and discrete interpretability tool for neural networks☆64Updated last year
- ☆33Updated 10 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆60Updated last year
- NeurIPS 2024 tutorial on LLM Inference☆47Updated 11 months ago
- Replicating O1 inference-time scaling laws☆90Updated 11 months ago
- Gemstones: A Model Suite for Multi-Faceted Scaling Laws (NeurIPS 2025)☆29Updated 2 months ago
- ☆88Updated last year
- The repository contains code for Adaptive Data Optimization☆28Updated 11 months ago
- Language models scale reliably with over-training and on downstream tasks☆100Updated last year
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆76Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆85Updated last year
- Code for ICML 2024 paper☆34Updated 2 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆92Updated last year
- ☆23Updated 10 months ago
- Efficient Scaling laws and collaborative pretraining.☆18Updated 2 months ago
- ☆94Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆145Updated 5 months ago
- Official repo of paper LM2☆46Updated 9 months ago
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆17Updated 7 months ago
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆61Updated last year
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆59Updated last month
- [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction☆79Updated 6 months ago
- Official repo for Learning to Reason for Long-Form Story Generation☆72Updated 7 months ago
- Using FlexAttention to compute attention with different masking patterns☆47Updated last year
- ☆110Updated 9 months ago
- Sparse Autoencoder Training Library☆55Updated 6 months ago
- ☆69Updated last year
- ☆27Updated 2 years ago
- A library for efficient patching and automatic circuit discovery.☆80Updated 4 months ago