Official code for Steering Large Language Models using Conceptors, presented at the NeurIPS 2024 MINT Workshop.
☆16Mar 13, 2025Updated last year
Alternatives and similar repositories for ConceptorSteering
Users that are interested in ConceptorSteering are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A very hacky set of functions for getting plotly to do what I want when doing mech interp research, designed to be compatible with PyTorc…☆15Jun 16, 2023Updated 3 years ago
- Official Code for What Makes and Breaks Safety Fine-tuning? A Mechanistic Study (NeurIPS 2024)☆11Oct 31, 2024Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆18Oct 21, 2025Updated 11 months ago
- Trains Sparse Autoencoders based on outputs from language models☆11Oct 7, 2024Updated 2 years ago
- ☆19Mar 5, 2024Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Tools for exploring Transformer neuron behaviour, including input pruning and diversification.☆25Sep 28, 2023Updated 3 years ago
- ☆12Jan 10, 2025Updated last year
- A Mechanistic Interpretability Analysis of Grokking☆29Sep 26, 2022Updated 4 years ago
- ☆17Oct 5, 2026Updated last week
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆30Nov 20, 2024Updated last year
- ☆43May 21, 2025Updated last year
- An exploration of LLM steering☆29Jun 15, 2024Updated 2 years ago
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆23Dec 14, 2024Updated last year
- Genertaes control vectors for use with llama.cpp in GGUF format.☆50Mar 19, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Sparse Autoencoder Training Library☆58May 1, 2025Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆255May 23, 2024Updated 2 years ago
- A curated lists of self-taught materials including research blogs☆16Dec 12, 2016Updated 9 years ago
- [ICLR26] Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs☆25Apr 8, 2026Updated 6 months ago
- ☆45Jul 3, 2026Updated 3 months ago
- ☆37Nov 16, 2025Updated 10 months ago
- Experiments with representation engineering☆14Feb 28, 2024Updated 2 years ago
- Building Llama 3 from scratch using PyTorch☆13Sep 1, 2024Updated 2 years ago
- ☆34Nov 28, 2024Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Codebase for Obfuscated Activations Bypass LLM Latent-Space Defenses☆33Feb 11, 2025Updated last year
- ☆14Apr 19, 2024Updated 2 years ago
- ☆23Aug 19, 2025Updated last year
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆15Feb 13, 2023Updated 3 years ago
- An API that detect expiration date from the product package's picture based on Deep Learning Algorithms☆11Jun 4, 2022Updated 4 years ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 8 months ago
- Tools for optimizing steering vectors in LLMs.☆22Apr 10, 2025Updated last year
- ☆18Jun 19, 2023Updated 3 years ago
- [TMLR 25] An automated method for explaining complex neuron behaviors in deep vision models using large language models☆12Feb 20, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆17Jul 4, 2025Updated last year
- Codes and data for AAAI-24 paper "Advancing Spatial Reasoning in Large Language Models: An In-depth Evaluation and Enhancement Using the …☆14Apr 23, 2024Updated 2 years ago
- ☆16Oct 29, 2025Updated 11 months ago
- Erasing conceptual knowledge from language models through low-rank fine-tuning☆25Mar 27, 2025Updated last year
- Code for reproducing the results from "CrAM: A Compression-Aware Minimizer" accepted at ICLR 2023☆10Mar 1, 2023Updated 3 years ago
- minimalistic AI library that resembles HF's transformers☆13Dec 31, 2024Updated last year
- Implementation of the paper: Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer.☆18Apr 23, 2023Updated 3 years ago