sparse-autoencoders

This paper applies sparse autoencoders to the CosyVoice3 text-to-speech language model, discovering interpretable features that can be steered to control attributes like laughter, speaker gender, and speech rate while preserving content.

This paper proposes a unified geometric framework for understanding concept learning and neuron interpretation in sparse autoencoders, formalizing concepts as sets and defining detection, separation, and approximation. It provides error bounds, capacity constraints, and links to formal concept analysis, with experiments on synthetic data.

This paper investigates whether auto-generated labels for sparse autoencoder features generalize across languages and scripts, using Serbian digraphia as a controlled testbed. It finds that while feature sets show substantial overlap across languages, the labels often fail to track the same concept in non-English inputs, particularly in less represented scripts.

Researchers extract indexable, BM25-ready sparse features from frozen dense retrievers using reconstruction-trained sparse autoencoders.

This paper presents a single-stage sparse coding method using unsupervised sparse autoencoders and natural inverted indexing to accelerate multi-vector retrieval, outperforming traditional k-means based approaches.

The paper proposes Latent Terms, a method using Sparse Autoencoders to extract BM25-ready sparse features from frozen dense retrievers, achieving competitive performance without retrieval-specific training.

This paper demonstrates that sparse autoencoders can extract interpretable features from Claude 3 Sonnet, a production-scale language model, addressing scalability concerns for dictionary learning. The features are multilingual, multimodal, and include safety-relevant concepts like deception and sycophancy, with causal influence on model outputs.

This paper introduces the readout-mediator angle to demonstrate that linear probes can decode information from language model activations that is orthogonal to the model's actual causal computation, undermining probe-based interpretability. The finding replicates across model scales and families, revealing a fundamental failure mode in using probes for mechanistic understanding or safety monitoring.

This paper uses Sparse Autoencoders to analyze the geometry of LoRA-induced representations in language models, finding that LoRA updates occupy partially distinct feature structures not fully captured by pretrained interpretability dictionaries.

This paper investigates the Platonic Representation Hypothesis, proposing that alignment arises from linear structure in representations, and introduces a statistical framework of signal, bias, and noise.

MechELK is a three-stage framework combining mechanistic interpretability tools (SAE, activation patching, causal probing) with representation engineering to elicit latent knowledge from LLMs, achieving 84.7% accuracy and outperforming existing methods like CCS and linear probing.

This paper introduces a bifurcation theory of representation dynamics to detect when neural networks acquire structured representations during training, using a Hessian analysis of a GMM probe. The resulting ratio β/β_c serves as a label-free phase coordinate that predicts the onset of usable structure and can forecast feature interpretability in sparse autoencoders early in training.

This paper introduces Prototype-Based Sparse Steering, a method that applies sparse autoencoders to attention query activations in LLMs, then uses gradient-based optimization during inference to steer generation toward target behaviors. The approach is validated in both a logical planning task and a stylistic educational domain, demonstrating interpretable and disentangled control.

This paper introduces a principled approach to multilingual language steering using sparse autoencoders (SAEs) trained on multilingual data and a novel layer selection rule based on the intersection of multilingual alignment and language separability, evaluated on LLaMA-3.1-8B and Gemma-2-9B for machine translation and cross-lingual summarization.

This paper uses sparse autoencoders to decompose LLMs into interpretable features and shows that semantic features explain brain alignment with cortical semantic topography, generalizing across English, Chinese, and French.

This paper presents a function-centric framework using Transcoders to trace computational pathways in vision-language models, demonstrating stronger attribution of visual grounding and the ability to predict hallucinations via graph-based features.

This paper proposes a five-stage methodology for causal feature analysis in transformer language models, demonstrated on GPT-2 small for the IOI task. It finds that features are specifically causal but not necessary, and exposes a gap between detection and causal robustness.

This article explores how sparse autoencoders (SAEs) can capture curved neural geometry, revealing three distinct ways SAE features represent manifolds, and presents an unsupervised pipeline to uncover geometric structure in neural representations.

This paper characterizes compositional literary primitives in instruction-tuned LLMs using sparse autoencoders, discovering feature classes for self, style, and affect that enable emotion steering across two architectures.

This paper introduces a diagnostic framework using Sparse Autoencoders to analyze concept-level forgetting in continual learning, finding that much forgetting is due to representational inaccessibility rather than erasure.