Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders

When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs

Sparse autoencoders (SAEs) are widely used to interpret the internal representations of large language models (LLMs), yet their reliability under post-hoc model compression remains poorly understood. We present a systematic study of how pruning affects SAE behavior and theoretically show that, for a fixed SAE, its impact is governed by perturbation energy, a covariance-weighted norm. This perspective exposes a key limitation of magnitude pruning: by ignoring activation geometry, it distorts the learned representation space and degrades SAE functionality. Activation-aware methods such as Wanda and SparseGPT, in contrast, implicitly control perturbation energy and are therefore substantially more robust at preserving SAE behavior. We further reveal a consistent structural vulnerability across all pruning methods: middle layers are significantly more sensitive to pruning than early or late layers. Guided by this insight, we propose a layer-wise sparsity allocation strategy, achieving lower perplexity under the same average pruning sparsity. Experiments across four model architectures validate our theoretical findings. Code is publicly available at https://github.com/osu-srml/sae-robustness-under-pruning/tree/main.

Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence

Within Explainable Artificial Intelligence, mechanistic interpretability uses Sparse Autoencoders (SAEs) to extract more interpretable features from neural representations. However, assessing their monosemanticity, and thus explanation quality, remains challenging. Existing metrics require external concept labels or depend on pretrained embedding models, making them sensitive to encoder's geometry. We introduce the Tversky Monosemanticity Score (TMS), a label-free metric that operationalizes monosemanticity as activation-set coherence of binarized SAE latents, and does not require external embedding encoders. We evaluate TMS on SAEs trained on features from pretrained vision and vision-language models (DINOv3, CLIP, BLIP2), two common SAE regimes (TopK, BatchTopK), multiple sparsity levels, and expansion factors. Our results show that TMS is less affected by encoder anisotropy than its embedding-based alternative, while remaining aligned with established monosemanticity indicators. TMS also reveals distinct SAE training dynamics across base models. Moreover, under encoder anisotropy, TMS provides a stronger indication of probe-based concept deletion effectiveness, while being competitive otherwise.

Beyond a Bag of Features: Set-Level Instability in Sparse Autoencoders

It is found that SAE activation sets do not recover human category boundaries or within-category typicality more faithfully than dense embeddings or residual-stream states, but instead track model-internal similarity structure.

SpIn-ViT: Designing a Sparsity-Induced Vision Transformer That Is Mechanistically Interpretable

Mechanistic interpretability has recently expanded to Vision Transformers (ViTs), with Sparse Autoencoders (SAEs) increasingly used as post-hoc tools to decompose internal representations into sparse and more interpretable features. However, because post-hoc SAEs are trained on frozen representations after the ViT has already been optimized, their latent features are not directly aligned with the downstream classification objective. We introduce SpIn-ViT, a framework that jointly trains a pretrained ViT and a modified SAE end-to-end, directly aligning sparse patch-level representations with image classification. SpIn-ViT learns semantically coherent neuron activations that localize meaningful image regions while maintaining competitive predictive performance. We evaluate SpIn-ViT across nine image-classification benchmarks using classification accuracy, quantitative interpretability metrics, AI-based and Human evaluations. Compared with the previous state-of-the-art post-hoc SAE method, SpIn-ViT achieves 8.84% higher average classification accuracy, an AI-based interpretability score nearly four times as high, and a human-evaluation score more than twice as high. We further extract interpretable rule-sets using the SAE neurons to create neurosymbolic models which achieve 5.97% higher average classification accuracy while requiring a 58.8\% smaller rule-set than the neurosymbolic models created from the SOTA post-hoc SAE method.

From Geometric Recovery to Causal Validation: A Reproducible Audit of Sparse Autoencoder Features, from Superposition Geometry to Causal Inertness

Sparse autoencoders (SAEs) are the standard for decomposing superposed neural representations into interpretable features, and evaluation relies predominantly on correlational recovery metrics -- cosine similarity between ground-truth directions and decoder atoms. We show this conflates two distinct claims: decoder-geometry alignment and encoder-activation behavior. We reproduce the superposition phase diagram of Elhage et al. (2022), identifying a convergence artifact at high sparsity and an under-described diffuse sharing regime at extreme overcompleteness. We reproduce the TopK-versus-L1 comparison of Gao et al. (2024), with direct evidence of L1 shrinkage. Our central result is causal: subjecting every recovered feature to ablation and steering, we find up to 77% of features passing a recovery bar (cosine>= 0.90) in a degraded SAE -- and 9% in a well-trained one -- are causally inert: the matched atom never fires when the feature is present, including matches at cosine ~1.000. We package the method as sae-causal-audit, a model-agnostic instrument with a deterministic pipeline. Re-auditing refines the finding: inertness decomposes by cause into structural inertness (antipodal-pair geometry, present in good SAEs) and competitive inertness (a TopK pathology of degraded SAEs), and by direction into read- and write-inertness, which five antipodal pairs dissociate completely -- unmonitorable yet steerable through the same atom, with steering specificities of 143-310 attached to zero ablation effects. We document why byte-exact reproducibility is unavailable by construction, and propose reporting it as a stack of claims with explicit scopes. Applying the instrument to a production SAE reproduces the pattern at small scale (14% inert) and surfaces an atom-collision signal: a handful of atoms recur as the nearest match for dozens of unrelated concepts, replicated across three batches.

Detoxifying Large Language Models via Localized Feature Editing with Sparse Autoencoders