Utilities for the HuggingFace transformers library
☆76Jan 21, 2023Updated 3 years ago
Alternatives and similar repositories for transformer-utils
Users that are interested in transformer-utils are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Mechanistic Interpretability for Transformer Models☆53Jun 1, 2022Updated 3 years ago
- ☆21Aug 18, 2022Updated 3 years ago
- Universal Neurons in GPT2 Language Models☆30May 28, 2024Updated last year
- Code to support the guide to logical induction for software engineers☆11Mar 24, 2025Updated last year
- ☆283Mar 2, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Jun 19, 2024Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆219Apr 27, 2026Updated last week
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆103Sep 21, 2023Updated 2 years ago
- ☆24Jul 25, 2024Updated last year
- Python SDK for Galileo's NLP and CV Studio.☆17Updated this week
- A case study of efficient training of large language models using commodity hardware.☆67Aug 4, 2022Updated 3 years ago
- ☆282Oct 1, 2024Updated last year
- Mechanistic Interpretability Visualizations using React☆342Apr 30, 2026Updated last week
- see github.com/understanding-search/maze-transformer☆10Dec 8, 2023Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- DiCE: The Infinitely Differentiable Monte-Carlo Estimator☆32Jul 28, 2023Updated 2 years ago
- The Happy Faces Benchmark☆15Jul 20, 2023Updated 2 years ago
- Pytorch implementation on OpenAI's Procgen ppo-baseline, built from scratch.☆14May 17, 2024Updated last year
- PyTorch-based library for various kinds of representational-similarity analysis☆25Jun 7, 2024Updated last year
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆23Feb 6, 2025Updated last year
- James' cookbook of evaluations and finetuning experiments☆26Feb 19, 2026Updated 2 months ago
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆18Nov 21, 2025Updated 5 months ago
- Source-to-Source Debuggable Derivatives in Pure Python☆15Jan 23, 2024Updated 2 years ago
- Tools for understanding how transformer predictions are built layer-by-layer☆586Aug 7, 2025Updated 9 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Python Research Framework☆107Nov 3, 2022Updated 3 years ago
- [Findings of NAACL2022] A Dog Is Passing Over The Jet? A Text-Generation Dataset for Korean Commonsense Reasoning and Evaluation☆11May 27, 2022Updated 3 years ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆917May 1, 2026Updated last week
- A library for mechanistic interpretability of GPT-style language models☆3,383Apr 30, 2026Updated last week
- ☆130Feb 10, 2026Updated 3 months ago
- ☆12Jul 21, 2024Updated last year
- Code for "Approaching Deep Learning through the Spectral Dynamics of Weights"☆13Oct 30, 2024Updated last year
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆13Feb 13, 2023Updated 3 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆256Feb 27, 2026Updated 2 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Erasing concepts from neural representations with provable guarantees☆249Jan 27, 2025Updated last year
- ☆48Sep 29, 2024Updated last year
- ☆562Feb 5, 2024Updated 2 years ago
- CoRelAy is a tool to compose small-scale (single-machine) analysis pipelines.☆32Apr 30, 2026Updated last week
- Training Sparse Autoencoders on Language Models☆1,361May 1, 2026Updated last week
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆47May 31, 2024Updated last year
- Codebase for Obfuscated Activations Bypass LLM Latent-Space Defenses☆31Feb 11, 2025Updated last year