#
sae
Here are 86 public repositories matching this topic...
A library for making RepE control vectors
machine-learning transformers language-model sparse-autoencoders sae sparse-autoencoder saes representation-engineering
-
Updated
Sep 24, 2025 - Jupyter Notebook
An Alibaba Cloud native microservice demo powered by Apache Dubbo and Spring Cloud Alibaba
-
Updated
Apr 28, 2025 - Java
Pivotal Token Search
tokens dataset-generation sae sparse-autoencoder dpo llm reasoning-agent llm-inference direct-preference-optimization llm-steering steering-vector phi-4 reasoning-language-models phi4 reasoning-models mech-interp phi4-mini phi-4-mini pivotal-token-search pivotal-tokens
-
Updated
Dec 20, 2025 - Python
A Deep Learning framework that analyses Windows PE files to detect malicious Softwares.
machine-learning deep-learning cnn python3 recurrent-neural-networks feature-extraction lstm neural-networks rnn feedforward-neural-network convolutional-neural-networks yara sae malware-detection fnn
-
Updated
Sep 12, 2025 - Python
Python Implementation of Zero Shot Learning Algorithms (ALE, DeViSE, ESZSL, SAE, SJE) under ZSLGBU protocol
-
Updated
May 19, 2020 - Python
Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)
-
Updated
Jul 24, 2025 - Python
Sparse Embedding Compression for Scalable Retrieval in Recommender Systems
-
Updated
Nov 21, 2025 - Python
Multi-Layer Sparse Autoencoders (ICLR 2025)
-
Updated
Feb 11, 2025 - Python
Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"
-
Updated
Oct 31, 2025 - Jupyter Notebook
Official Triton kernels for TopK and HierarchicalTopK Sparse Autoencoder decoders.
-
Updated
Sep 29, 2025 - Python
Explore visualization tools for understanding Transformer-based large language models (LLMs)
visualization awesome interactive transformer attention-mechanism bert gemma interactive-visualizations sae sparse-autoencoder explainable-ai large-language-models llm mechanistic-interpretability
-
Updated
Dec 1, 2024
Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.
vit fine-tune clip sae adversarial-learning sparse-autoencoder finetune fine-tuning adversarial-attacks vision-transformer
-
Updated
Dec 19, 2024 - Python
Interpreting CLIP with Hierarchical Sparse Autoencoders (ICML 2025)
-
Updated
Jan 17, 2026 - Jupyter Notebook
Zero-copy parser for SAE J2735 UPER-encoded V2X messages. O(1) field access for embedded RSU/OBU firmware.
c embedded high-performance zero-copy asn1 header-only automotive v2x sae its dsrc uper connected-vehicles j2735 x691
-
Updated
Jan 1, 2026 - C
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"
-
Updated
Jan 26, 2025 - Python
Improve this page
Add a description, image, and links to the sae topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the sae topic, visit your repo's landing page and select "manage topics."