# FADE: Why Bad Descriptions Happen to Good Features

arXiv: https://arxiv.org/abs/2502.16994 · HTML: https://mlsanity.com/paper/2502.16994/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in SAE features and their applications, one of 13 directions in Mechanistic interpretability.
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Placed in

- Mechanistic interpretability / [SAE features and their applications](https://mlsanity.com/mechinterp/sae-features-and-their-applications/)

## Builds on (most cited first, 14 of 14)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2](https://mlsanity.com/paper/2408.05147/) (2024)
- [Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders](https://mlsanity.com/paper/2407.14435/) (2024)
- [A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity](https://mlsanity.com/paper/2401.01967/) (2024)
- [Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control](https://mlsanity.com/paper/2405.08366/) (2024)
- [Erasing Conceptual Knowledge from Language Models](https://mlsanity.com/paper/2410.02760/) (2024)
- [Labeling Neural Representations with Inverse Recognition](https://mlsanity.com/paper/2311.13594/) (2023)
- [Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers](https://mlsanity.com/paper/2501.17727/) (2025)
- [Mechanistic understanding and validation of large AI models with SemanticLens](https://mlsanity.com/paper/2501.05398/) (2025)
- [CoSy: Evaluating Textual Explanations of Neurons](https://mlsanity.com/paper/2405.20331/) (2024)
- [Analyzing (In)Abilities of SAEs via Formal Languages](https://mlsanity.com/paper/2410.11767/) (2024)

## Built on by (most cited first, 13 of 13)

- [Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework](https://mlsanity.com/paper/2506.15538/) (2025)
- [Circuit Insights: Towards Interpretability Beyond Activations](https://mlsanity.com/paper/2510.14936/) (2025)
- [Interpreting Language Models Through Concept Descriptions: A Survey](https://mlsanity.com/paper/2510.01048/) (2025)
- [Atlas-Alignment: Making Interpretability Transferable Across Language Models](https://mlsanity.com/paper/2510.27413/) (2025)
- [Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language](https://mlsanity.com/paper/2510.06378/) (2025)
- [Interpreto: An Explainability Library for Transformers](https://mlsanity.com/paper/2512.09730/) (2025)
- [Prune, Interpret, Evaluate: A Cross-Layer Transcoder-Native Framework for Efficient Circuit Discovery via Feature Attribution](https://mlsanity.com/paper/2604.16889/) (2026)
- [Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge](https://mlsanity.com/paper/2605.16023/) (2026)
- [Steering grids for sparse-autoencoder features: when a top-context label names an activation regime rather than a causal axis](https://mlsanity.com/paper/2605.03160/) (2026)
- [Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance](https://mlsanity.com/paper/2607.19386/) (2026)
- [SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization](https://mlsanity.com/paper/2608.13538/) (2026)
- [SharedSAE: One Feature Dictionary Across Language Models](https://mlsanity.com/paper/2609.04344/) (2026)
- [Identifying Temporal Features within Transcoders for Time Sensitive Factual Recall](https://mlsanity.com/paper/2609.33183/) (2026)

## Abstract (arXiv)

Recent advances in mechanistic interpretability have highlighted the potential of automating interpretability pipelines in analyzing the latent representations within LLMs. While this may enhance our understanding of internal mechanisms, the field lacks standardized evaluation methods for assessing the validity of discovered features. We attempt to bridge this gap by introducing FADE: Feature Alignment to Description Evaluation, a scalable model-agnostic framework for automatically evaluating feature-to-description alignment. FADE evaluates alignment across four key metrics - Clarity, Responsiveness, Purity, and Faithfulness - and systematically quantifies the causes of the misalignment between features and their descriptions. We apply FADE to analyze existing open-source feature descriptions and assess key components of automated interpretability pipelines, aiming to enhance the quality of descriptions. Our findings highlight fundamental challenges in generating feature descriptions, particularly for SAEs compared to MLP neurons, providing insights into the limitations and future directions of automated interpretability. We release FADE as an open-source package at: https://github.com/brunibrun/FADE