Studio Franco
← Back to Portfolio
AI + Hardware

LOBE

Mechanistic Interpretability & Steering Toolkit

AI / Interpretability Python Transformers

What it is

LOBE is a modular Python framework for real-time activation steering and causal feature validation in transformer architectures. It implements a RuntimeController and a hook-based intervention engine that lets you scale latent features during inference, steering the model's behavior directly without retraining.

How it works

The core is a hook-based intervention engine that registers forward hooks on transformer layers, capturing activations as they flow through the model. A RuntimeController applies alpha-scaled deltas to targeted latent features, letting you amplify or suppress specific concepts (e.g. "honesty," "refusal") at inference time.

controller = RuntimeController(model)
controller.register_hook(layer="blocks.5.hook_resid_pre", feature="honesty")
controller.steer(feature="honesty", alpha=1.5)
output = model.generate(prompt)

CausalSweeper validates feature-trait correlations by measuring behavioral change across alpha-scaled activation deltas, giving you a causal read on which features actually drive which outputs.

Stack

  • Python
  • PyTorch
  • TransformerLens
  • Hook-based intervention engine
  • Causal feature validation

Status

Experimental: built to explore how model internals can be steered causally.