PaulPauls / llama3_interpretability_sae
A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
☆606Updated 3 weeks ago
Alternatives and similar repositories for llama3_interpretability_sae:
Users that are interested in llama3_interpretability_sae are comparing it to the libraries listed below
- A library for making RepE control vectors☆569Updated 3 months ago
- LLM Analytics☆654Updated 5 months ago
- Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…☆281Updated last month
- Open weights language model from Google DeepMind, based on Griffin.☆632Updated last month
- Visualize the intermediate output of Mistral 7B☆354Updated 2 months ago
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆302Updated 5 months ago
- Dead Simple LLM Abliteration☆210Updated last month
- An interactive HTML pretty-printer for machine learning research in IPython notebooks.☆402Updated 3 weeks ago
- Felafax is building AI infra for non-NVIDIA GPUs☆558Updated 2 months ago
- A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private co…☆233Updated this week
- Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).☆250Updated last year
- A scientific instrument for investigating latent spaces☆685Updated last month
- ☆243Updated last year
- Stop messing around with finicky sampling parameters and just use DRµGS!☆348Updated 10 months ago
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆342Updated 8 months ago
- Diffusion on syntax trees for program synthesis☆451Updated 9 months ago
- Things you can do with the token embeddings of an LLM☆1,435Updated 2 weeks ago
- See Through Your Models☆374Updated last month
- Textbook on reinforcement learning from human feedback☆547Updated this week
- ☆742Updated 11 months ago
- Neural Search☆353Updated last month
- Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.☆566Updated last month
- A pure NumPy implementation of Mamba.☆221Updated 9 months ago
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆204Updated 4 months ago
- Aidan Bench attempts to measure <big_model_smell> in LLMs.☆290Updated this week
- An implementation of bucketMul LLM inference☆216Updated 9 months ago
- Lightweight Nearest Neighbors with Flexible Backends☆264Updated last month
- Distributed Training Over-The-Internet☆895Updated 4 months ago
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,752Updated this week
- System 2 Reasoning Link Collection☆824Updated 3 weeks ago