harish-kamath / rqae
Residual Quantization Autoencoder, used for interpreting LLMs
☆11Updated 3 months ago
Alternatives and similar repositories for rqae:
Users that are interested in rqae are comparing it to the libraries listed below
- Minimum Description Length probing for neural network representations☆19Updated 2 months ago
- Aioli: A unified optimization framework for language model data mixing☆23Updated 3 months ago
- Code for experiments on self-prediction as a way to measure introspection in LLMs☆13Updated 4 months ago
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Updated last year
- ☆33Updated 2 weeks ago
- ☆34Updated last year
- Closed-form polynomial approximations to neural networks☆12Updated 2 months ago
- ☆18Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated 10 months ago
- Efficient Scaling laws and collaborative pretraining.☆16Updated 2 months ago
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.☆27Updated last month
- Implementation of Spectral State Space Models☆16Updated last year
- ☆21Updated 4 months ago
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆15Updated 3 years ago
- Source-to-Source Debuggable Derivatives in Pure Python☆15Updated last year
- Experiments on GPT-3's ability to fit numerical models in-context.☆14Updated 2 years ago
- ☆21Updated 3 weeks ago
- Ranking of fine-tuned HF models as base models.☆35Updated last year
- 🧮 Algebraic Positional Encodings.☆12Updated 3 months ago
- ☆14Updated 6 months ago
- LLM training in simple, raw C/CUDA☆14Updated 4 months ago
- Evaluation of neuro-symbolic engines☆35Updated 8 months ago
- Understanding how features learned by neural networks evolve throughout training☆34Updated 6 months ago
- ☆26Updated last year
- Embedding Recycling for Language models☆38Updated last year
- ☆16Updated 6 months ago
- A quick way to get started with Transformer Lens☆14Updated last year
- ☆49Updated last year
- PyTorch Implementation of the paper "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"☆23Updated this week
- ☆29Updated last year