interpretability

Chat2Graph: Graph Native Agentic System.

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

This repository introduces MentaLLaMA, the first open-source instruction following large language model for interpretable mental health analysis.

Diffusers-Interpret 🤗🧨🕵️‍♀️: Model explainability for 🤗 Diffusers. Get explanations for your generated images.

Interpretable Causal Diffusion Language Models

To know what models don't say out loud.

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.

A python package for benchmarking interpretability techniques on Transformers.

Interpret text data with LLMs (sklearn compatible).

A library for finding knowledge neurons in pretrained transformer models.

Collection of NLP model explanations and accompanying analysis tools

[ICLR 2026] DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning

Robust multimodal image registration via keypoints

Generating and validating natural-language explanations for the brain.

Sparse and discrete interpretability tool for neural networks

An interpretable foundation model of the patient clinical timeline: event forecasting, calibrated time-to-event alerts, and concept-level interpretability, benchmarked head-to-head against tuned GBMs, tabular foundation models, and survival baselines on MIMIC-IV, eICU, and GEMINI via the MEDS standard.

Time series explainability via self-supervised model behavior consistency

OpenAI-compatible server with a live view into any HF model's residual stream. pip install brainscope

Code for the paper "Aligning LLM Agents by Learning Latent Preference from User Edits".

Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.