Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance

• URL: http://arxiv.org/abs/2605.31304v1
• Date: Fri, 29 May 2026 13:39:09 GMT
• Title: Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance
• Abstract summary: ELUDe is a method for improving the interpretability of deep neural networks.<n>It breaks latent representations into clear, inspectable sub-units that behave like interpretable features.<n>It requires no explicit training, no labels, and can be applied to pretrained models.
• Score: 58.49623467782041
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks (DNNs) are widely used, but interpreting what they actually learn remains difficult. A major obstacle is that individual neurons often encode multiple unrelated concepts, obscuring the decision process of the network. While prior work, such as sparse autoencoders, can separate these mixed signals into more meaningful, "monosemantic" features, this typically requires altering the model in ways that can degrade downstream performance. To overcome this, we introduce ELUDe (explicit, lossless, unsupervised disentanglement), a method for improving the interpretability of DNNs while preserving their functional equivalence. ELUDe breaks latent representations into clear, inspectable sub-units that behave like interpretable features, while guaranteeing that the model's outputs remain exactly the same. It requires no explicit training, no labels, and can be applied to pretrained models. ELUDe works by reorganizing how information flows between layers, re-routing concept-specific contributions while preserving the original computation by construction. Across several vision models, including DINOv2 and supervised ViT-B/16, ELUDe improves interpretability, keeps downstream accuracy unchanged, runs efficiently, and supports practical uses such as steering model representations. In short, ELUDe offers interpretability (almost) without a tradeoff: clearer, scalable, and actionable model insights with no loss in performance.

Related papers

• Where Does Generative Difficulty Reside? An Empirical Study of Target Representations [62.54876287800644]
  The target representation defines the distribution an image generator must learn, yet it is often treated as an interchangeable interface.<n>We study raw pixels, SD-VAE latents and DINOv2 as well as MAE representation-autoencoder features within a unified masked autoregressive rectified-flow model.<n>Our results show that compression, reconstruction fidelity, token dimensionality, and visible semantic clustering do not individually predict generative behavior.
  arXiv  Detail & Related papers  (2026-08-01T12:32:31Z)
• Sparse but not Simpler: A Multi-Level Interpretability Analysis of Vision Transformers [5.6842776317118835]
  We evaluate the relationship between weight sparsity and interpretability in Vision Transformers using DeiT-III B/16 models pruned with Wanda.<n>Our results reveal a clear structural effect but limited interpretability gains.<n>These findings suggest that structural sparsity alone does not reliably yield more interpretable vision models.
  arXiv  Detail & Related papers  (2026-03-16T21:13:49Z)
• Efficient Representations are Controllable Representations [0.0]
  Controlling how LLMs internally represent concepts requires sophisticated methods to first identify, then intervene on the model's existing feature geometry.<n>We finetune an LLM with a simple auxiliary loss, training 16 of its 3072 residual stream dimensions to be inert interpretability flags that simply indicate what concepts are required for generation.<n>As a result, these inert flags become genuine internal features: interpretable control switches that allow us to steer generation at inference time.
  arXiv  Detail & Related papers  (2026-02-08T05:32:02Z)
• Learning a Generative Meta-Model of LLM Activations [75.30161960337892]
  We create "meta-models" that learn the distribution of a network's internal states.<n>Applying the meta-model's learned prior to steering interventions improves fluency, with larger gains as loss decreases.<n>These results suggest generative meta-models offer a scalable path toward interpretability without restrictive structural assumptions.
  arXiv  Detail & Related papers  (2026-02-06T18:59:56Z)
• Interpret the Internal States of Recommendation Model with Sparse Autoencoder [28.234859617081295]
  RecSAE is an automated and generalizable probing framework that interprets Recommenders with Sparse AutoEncoder.<n>It extracts interpretable latents from the internal states of recommendation models and links them to semantic concepts for interpretation.<n> RecSAE does not alter original models during interpretation and also enables targeted de-biasing to models based on interpreted results.
  arXiv  Detail & Related papers  (2024-11-09T08:22:31Z)
• Augmenting Interpretable Models with LLMs during Training [73.40079895413861]
  We propose Augmented Interpretable Models (Aug-imodels) to build efficient and interpretable models. Aug-imodels use LLMs during fitting but not during inference, allowing complete transparency. We explore two instantiations of Aug-imodels in natural-language processing: (i) Aug-GAM, which augments a generalized additive model with decoupled embeddings from an LLM and (ii) Aug-Tree, which augments a decision tree with LLM feature expansions.
  arXiv  Detail & Related papers  (2022-09-23T18:36:01Z)
• Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps [85.49020931411825]
  Convolutional Neural Networks (CNNs) compression is crucial to deploying these models in edge devices with limited resources. We propose to address the channel pruning problem from a novel perspective by leveraging the interpretations of a model to steer the pruning process. We tackle this challenge by introducing a selector model that predicts real-time smooth saliency masks for pruned models.
  arXiv  Detail & Related papers  (2022-09-07T01:12:11Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Combining Discrete Choice Models and Neural Networks through Embeddings: Formulation, Interpretability and Performance [10.57079240576682]
  This study proposes a novel approach that combines theory and data-driven choice models using Artificial Neural Networks (ANNs) In particular, we use continuous vector representations, called embeddings, for encoding categorical or discrete explanatory variables. Our models deliver state-of-the-art predictive performance, outperforming existing ANN-based models while drastically reducing the number of required network parameters.
  arXiv  Detail & Related papers  (2021-09-24T15:55:31Z)
• It's FLAN time! Summing feature-wise latent representations for interpretability [0.0]
  We propose a novel class of structurally-constrained neural networks, which we call FLANs (Feature-wise Latent Additive Networks) FLANs process each input feature separately, computing for each of them a representation in a common latent space. These feature-wise latent representations are then simply summed, and the aggregated representation is used for prediction.
  arXiv  Detail & Related papers  (2021-06-18T12:19:33Z)
• Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs [19.398202091883366]
  We present an approach based on INNs that (i) recovers the task-specific, learned invariances by disentangling the remaining factor of variation in the data and that (ii) invertibly transforms these invariances combined with the model representation into an equally expressive one with accessible semantic concepts. Our invertible approach significantly extends the abilities to understand black box models by enabling post-hoc interpretations of state-of-the-art networks without compromising their performance.
  arXiv  Detail & Related papers  (2020-08-04T19:27:46Z)
• Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck [52.08901549360262]
  Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. VAEs tend to ignore latent variables with a strong auto-regressive decoder. We propose a principled approach to enforce an implicit latent feature matching in a more compact latent space.
  arXiv  Detail & Related papers  (2020-04-22T14:41:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.