Decoding the black box of LLMs: A comparative analysis of Logit Lens vs. Tuned Lens to interpret intermediate Transformer layers in GPT-2.
-
Updated
Apr 2, 2026 - Jupyter Notebook
#
tuned-lens
Here are 5 public repositories matching this topic...
From-scratch PyTorch implementation of the Tuned Lens (Belrose et al., 2023) — learned per-layer affine probes that sharpen intermediate transformer predictions beyond the raw logit lens.
-
Updated
Apr 1, 2026 - Python
Code and artifacts for The Convergence Gap: when instruction-tuned models settle on next-token predictions.
language-models reproducibility early-exit large-language-models instruction-tuning mechanistic-interpretability llm-interpretability model-diffing tuned-lens convergence-gap
-
Updated
Aug 11, 2026 - Python
Cross-architecture mechanistic interpretability toolkit — first OSS Mamba SSM state extraction. Works on transformer + SSM + hybrid models with unified API.
pytorch transformer probes ssm mamba sparse-autoencoders ai-safety interpretability state-space-models cross-architecture llm mechanistic-interpretability activation-patching mech-interp tuned-lens
-
Updated
May 15, 2026 - Python
Research workspace for model diffing between pretrained and post-trained language models.
transcoder llama sae post-training instruction-tuning mechanistic-interpretability qwen deepseek olmo llm-interpretability gemma3 model-diffing tuned-lens cross-patching
-
Updated
Aug 11, 2026 - Python
Add this topic to your repo
To associate your repository with the tuned-lens topic, visit your repo's landing page and select "manage topics."