Code for the paper "A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders"
☆18Dec 28, 2025Updated 10 months ago
Alternatives and similar repositories for sae-spelling
Users that are interested in sae-spelling are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆34Oct 20, 2026Updated last week
- Fluent dreaming for language models☆14Jul 22, 2024Updated 2 years ago
- An experimental tool to explore GPT-3's "miraculous" ability not only to spell its own token strings (it being a "character blind" model)…☆12Oct 3, 2023Updated 3 years ago
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆19Jul 6, 2026Updated 3 months ago
- Code for experiments on transformers using Markovian data.☆22Nov 22, 2024Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- A python package for protein inference in Mass Spectrometric data analysis.☆10Jun 6, 2022Updated 4 years ago
- Collection of LLM completions for reasoning-gym task datasets☆32Jul 4, 2025Updated last year
- [NeurIPS 2025] PRISM is a multi-concept feature description framework which can identify and score polysemantic features.☆14Jun 26, 2026Updated 4 months ago
- [ACL 2023] Gradient Ascent Post-training Enhances Language Model Generalization☆29Sep 12, 2024Updated 2 years ago
- ☆435Aug 21, 2025Updated last year
- A python plugin integrated into Carla Simulator for emulate cyber-attack over the CAN-Bus (https://carla.org/)☆15Apr 26, 2021Updated 5 years ago
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆23Feb 6, 2025Updated last year
- Complexity vs. Accuracy: On Mechanistic Interpretability's Dependence on the Linear Representation Hypothesis☆14Oct 9, 2025Updated last year
- ☆14Oct 6, 2026Updated 3 weeks ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- F# scripting and Fable Repl combo!☆11Nov 1, 2018Updated 7 years ago
- Sample Level Analysis of Pathway Alteration Enrichments☆10Jan 21, 2019Updated 7 years ago
- Repository for the SVD directions less wrong post☆12Dec 18, 2022Updated 3 years ago
- A Tool to visualize NN training☆15Feb 21, 2026Updated 8 months ago
- ☆12Sep 11, 2025Updated last year
- tugHall: a simulator of cancer cell evolution based on the hallmarks of cancer, linked to the mutational states of tumor-related genes. T…☆13Dec 11, 2023Updated 2 years ago
- Examples using the Leap Interpretability Engine!☆10Dec 22, 2023Updated 2 years ago
- ☆186May 1, 2026Updated 5 months ago
- Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner☆31Jun 27, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆16Oct 23, 2023Updated 3 years ago
- Codebase for Temporal SAEs paper☆28Nov 14, 2025Updated 11 months ago
- Competing Genetic Algorithm to find profitable Trading Strategies on a financial market☆13May 29, 2019Updated 7 years ago
- ☆113May 23, 2026Updated 5 months ago
- ASCETIC (Agony-baSed Cancer EvoluTion InferenCe) is a novel framework for the inference of a set of statistically significant temporal pa…☆12Apr 18, 2025Updated last year
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆20Jun 7, 2023Updated 3 years ago
- ☆11Feb 9, 2024Updated 2 years ago
- Scaling Laws for Mixture of Experts Models☆16Feb 25, 2025Updated last year
- ☆29Apr 30, 2024Updated 2 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Lang…☆24Jul 3, 2024Updated 2 years ago
- ☆38Apr 30, 2024Updated 2 years ago
- ☆16Jun 26, 2026Updated 4 months ago
- ☆14Dec 4, 2024Updated last year
- R implementation of the BAGEL method to call for gene essentiality significance☆11May 1, 2018Updated 8 years ago
- Sparse Autoencoder for Mechanistic Interpretability☆308Jul 20, 2024Updated 2 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆277Feb 27, 2026Updated 8 months ago