activation-patch

Here are 4 public repositories matching this topic...

divyanshddn146 / contextual-integrity-circuit

Mechanistic study of contextual-integrity post-training in Qwen2.5-7B, testing whether improved privacy behavior comes from new mechanisms or better use of machinery already present in the base model.

privacy language-model ai-safety interpretability qwen-7b llm-interpretability model-diffing causal-interventions contextual-integrity activation-patch

Updated Sep 22, 2026
Python

Samimj9 / llmexplorer

Star

A research library for mechanistic interpretability and Theory of Mind in large language models

theory-of-mind large-language-models llm mechanisticinterpretability activation-patch

Updated Aug 31, 2026
Python

divyanshddn146 / same-behaviour-different-mechanisms

Star

Code and processed results for a cross-model causal analysis of subject–verb agreement control in Phi-2, Llama-3.2-3B, and Qwen2.5-3B.

nlp transformers language-models subject-verb-agreement causal-analysis mechanistic-interpretability activation-steering activation-patch

Updated Sep 4, 2026
Python

2betforyou / medical-ai-linear-probe

Star

Does clinical co-occurrence strength predict when a medical VLM's internal representation of a finding is decodable but not causally used? Interpretability study on CheXagent-2-3b using activation probing and patching.

deep-learning medical-imaging radiology causal-inference interpretability probing chest-xray hallucination mechanistic-interpretability vision-language-model activation-patch explainable-algorithms

Updated Aug 20, 2026
Python

Add this topic to your repo

To associate your repository with the activation-patch topic, visit your repo's landing page and select "manage topics."

Learn more