bartbussmann / BatchTopK
Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)
☆27Updated 6 months ago
Alternatives and similar repositories for BatchTopK:
Users that are interested in BatchTopK are comparing it to the libraries listed below
- ☆62Updated this week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆44Updated 4 months ago
- ☆17Updated 10 months ago
- ☆32Updated 2 weeks ago
- ☆159Updated this week
- ☆120Updated last year
- ☆60Updated 3 months ago
- ☆25Updated last month
- Sparse Autoencoder Training Library☆42Updated 4 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 9 months ago
- ☆80Updated 7 months ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆25Updated 11 months ago
- A library for efficient patching and automatic circuit discovery.☆56Updated 3 weeks ago
- ☆21Updated 2 weeks ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆71Updated 4 months ago
- Using sparse coding to find distributed representations used by neural networks.☆218Updated last year
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆18Updated last month
- ☆26Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆29Updated 9 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆70Updated 3 months ago
- Sparse probing paper full code.☆55Updated last year
- ☆88Updated last month
- Sparse and discrete interpretability tool for neural networks☆59Updated last year
- ☆16Updated this week
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆60Updated last month
- ☆26Updated 11 months ago
- ☆31Updated 3 months ago
- ☆251Updated last month
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆184Updated 2 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆40Updated 5 months ago