Probing whether induction head universality is truly architecture-agnostic or whether model family leaves a structural fingerprint on the circuits that enable in-context learning.
-
Updated
Jul 6, 2026 - Python
#
interpretability-experiments
Here are 3 public repositories matching this topic...
Probing where in Pythia's residual stream the decision to be sycophantic is already 'decided', using linear classifiers on per-layer activations against a small labeled sycophancy dataset.
-
Updated
May 4, 2026 - Python
A hypothesis of depth-indexed state regimes in pre-RMSNorm language models.
machine-learning deep-learning transformers neural-networks deep-learning-papers interpretability ai-research activation-analysis deep-learning-projects llm llms mechanistic-interpretability rmsnorm transformers-architecture residual-stream interpretability-research interpretability-experiments residual-streams scheduled-transformer
-
Updated
Sep 22, 2026 - HTML
Add this topic to your repo
To associate your repository with the interpretability-experiments topic, visit your repo's landing page and select "manage topics."