IndexMapAnti-DoomscrollAbout
See also
ConceptLLMCross-Modal

Mechanistic Interpretability

Also known as: Mech Interp · Transformer Circuits · Sparse Autoencoders · SAEs · Dictionary Learning · Monosemanticity · Attribution Graphs · Cross-Layer Transcoders

Plain English

A research discipline that reverse-engineers neural networks from the inside out—mapping hidden weights and activations into human-understandable concepts and circuits. Rather than judging an AI model only by its final outputs, mechanistic interpretability examines the internal algorithms it executes.

Technical Overview

Mechanistic interpretability decomposes Transformer residual streams, QK/OV attention circuits, and MLP layers into sparse, causal components even when superposition packs far more features than neurons into polysemantic activations. Unsupervised dictionary learning—using sparse autoencoders (SAEs) and cross-layer transcoders (CLTs)—extracts monosemantic concepts and reconstructs multi-step attribution graphs across production models (Anthropic's Transformer Circuits, Google DeepMind's Gemma Scope 2). By 2025–2026, methods expanded beyond post-hoc SAEs to natively weight-sparse circuits (OpenAI) and Natural Language Autoencoders that verbalize activations directly for safety auditing and evaluation awareness detection.

Timeline (6)

RSS
  1. 2021

  2. 2023

  3. 2024

  4. 2025

    Paper

    Ameisen, Lindsey, and Anthropic's interpretability team published Circuit Tracing and On the Biology of a Large Language Model, using cross-layer transcoders (CLTs) to construct feature attribution graphs in Claude 3.5 Haiku—revealing multi-hop reasoning, advance rhyme planning, and shared cross-lingual concept spaces before open-sourcing circuit-tracer in May 2025.

  5. 2026

    Paper

    Fraser-Taliente, Kantamneni, Ong, and colleagues introduced Natural Language Autoencoders (NLAs), jointly training an activation verbalizer and reconstructor with reinforcement learning so residual-stream states decode directly into natural-language explanations—surfacing unverbalized task strategies and evaluation awareness without manual feature labeling, alongside July 2026's Jacobian-lens Global Workspace study (arXiv:2607.15495).

See also (10)

Open full graph
5 more connections