MaheepChaudhary / SAE-RavelLinks
Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the paper "Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small"
☆11Updated 4 months ago
Alternatives and similar repositories for SAE-Ravel
Users that are interested in SAE-Ravel are comparing it to the libraries listed below
Sorting:
- ☆44Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆47Updated 8 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆60Updated 6 months ago
- General-purpose activation steering library☆78Updated last month
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- ☆29Updated last year
- Align your LM to express calibrated verbal statements of confidence in its long-form generations.☆26Updated last year
- ☆14Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆95Updated 2 weeks ago
- Restore safety in fine-tuned language models through task arithmetic☆28Updated last year
- ☆44Updated 3 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆27Updated last year
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆37Updated 7 months ago
- This repository contains data, code and models for contextual noncompliance.☆23Updated 11 months ago
- ☆95Updated last year
- ☆34Updated 6 months ago
- Code for the paper "Spectral Editing of Activations for Large Language Model Alignments"☆24Updated 6 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆35Updated last year
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆30Updated 5 months ago
- Learning adapter weights from task descriptions☆19Updated last year
- Augmenting Statistical Models with Natural Language Parameters☆27Updated 9 months ago
- ☆26Updated 4 months ago
- [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors☆77Updated 6 months ago
- ☆35Updated last month
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆58Updated 2 weeks ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 3 months ago
- ☆16Updated last year
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]☆17Updated last year
- ☆51Updated last year
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆27Updated last year