EleutherAI / features-across-time
Understanding how features learned by neural networks evolve throughout training
☆32Updated 2 months ago
Alternatives and similar repositories for features-across-time:
Users that are interested in features-across-time are comparing it to the libraries listed below
- Minimum Description Length probing for neural network representations☆18Updated last week
- Sparse and discrete interpretability tool for neural networks☆58Updated 11 months ago
- ☆67Updated 5 months ago
- Code associated to papers on superposition (in ML interpretability)☆26Updated 2 years ago
- Evaluation of neuro-symbolic engines☆34Updated 5 months ago
- ☆25Updated 2 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆28Updated 2 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆66Updated last month
- Experiments for efforts to train a new and improved t5☆77Updated 9 months ago
- The repository contains code for Adaptive Data Optimization☆21Updated last month
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆66Updated 2 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 7 months ago
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated last year
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆81Updated 2 months ago
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated 7 months ago
- gzip Predicts Data-dependent Scaling Laws☆33Updated 7 months ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆28Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆52Updated last year
- One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation☆36Updated 3 months ago
- Official implementation of "BERTs are Generative In-Context Learners"☆23Updated 7 months ago
- Latent Large Language Models☆17Updated 4 months ago
- ☆33Updated 4 months ago
- Universal Neurons in GPT2 Language Models☆27Updated 7 months ago
- ☆21Updated last week
- ☆69Updated 5 months ago
- Efficient Dictionary Learning with Switch Sparse Autoencoders (SAEs)☆16Updated last month
- ☆115Updated this week
- Embedding Recycling for Language models☆38Updated last year
- ☆72Updated 8 months ago