As AI systems grow increasingly complex, understanding their behavior remains a critical challenge [Arrieta et al., 2020, Longo et al., 2024]. Researchers have developed methods to explain AI systems by attributing their behavior to three distinct aspects: input features, training data, and internal model components. Feature attribution methods identify influence of input features at test time, revealing which aspects of the input drive the model's output [Zeiler and Fergus, 2014, Ribeiro et al., 2016, Horel and Giesecke, 2020, 2022, Lundberg and Lee, 2017, Smilkov et al., 2017]. Data attribution analyzes how training data shape model behavior during the training phase [Koh and Liang, 2017, Ghorbani and Zou, 2019, Ilyas et al., 2022]. Component attribution examines the internal workings of the model by analyzing how specific components, such as neurons or layers in a neural network (NN), affect model behavior [Vig et al., 2020, Meng et al., 2022, Nanda, 2023, Shah et al., 2024]. While numerous attribution methods have been developed for each of these three aspects, and some survey papers have been published [Guidotti et al., 2018, Covert et al., 2021, Wang et al., 2024, Hammoudeh and Lowd, 2024, Bereska and Gavves, 2024], they have been studied and used rather independently by different communities, creating a fragmented landscape of methods and terminology for similar ideas [Saphra and Wiegreffe, 2024]. Our position is that feature, data, and component attribution methods can be bridged to advance not only interpretability research, by stimulating cross-aspect knowledge transfer, but also broader AI research, including model editing, steering, and regulation. We show that these three types of attribution employ common methods and they differ primarily in perspective rather than core techniques.

With the growing complexity and capability of large language models, a need to understand model reasoning has emerged, often motivated by an underlying goal of controlling and aligning models. While numerous interpretability and steering methods have been proposed as solutions, they are typically designed either for understanding or for control, seldom addressing both, with the connection between interpretation and control more broadly remaining tenuous. Additionally, the lack of standardized applications, motivations, and evaluation metrics makes it difficult to assess these methods' practical utility and efficacy. To address this, we propose intervention as a fundamental goal of interpretability and introduce success criteria to evaluate how well methods are able to control model behavior through interventions. We unify and extend four popular interpretability methods--sparse autoencoders, logit lens, tuned lens, and probing--into an abstract encoder-decoder framework. This framework maps intermediate latent representations to human-interpretable feature spaces, enabling interventions on these interpretable features, which can then be mapped back to latent representations to control model outputs. We introduce two new evaluation metrics: intervention success rate and the coherence-intervention tradeoff, designed to measure the accuracy of explanations and their utility in controlling model behavior. Our findings reveal that (1) although current methods allow for intervention, they are inconsistent across models and features, (2) lens-based methods outperform others in achieving simple, concrete interventions, and (3) interventions often compromise model performance and coherence, underperforming simpler alternatives, such as prompting, for steering model behavior and highlighting a critical shortcoming of current interpretability approaches in real-world applications requiring control.

Do different generative image models secretly learn similar underlying representations? We investigate this by measuring the latent space similarity of four different models: VAEs, GANs, Normalizing Flows (NFs), and Diffusion Models (DMs). Our methodology involves training linear maps between frozen latent spaces to "stitch" arbitrary pairs of encoders and decoders and measuring output-based and probe-based metrics on the resulting "stitched'' models. Our main findings are that linear maps between latent spaces of performant models preserve most visual information even when latent sizes differ; for CelebA models, gender is the most similarly represented probe-able attribute. Finally we show on an NF that latent space representations converge early in training.

As Artificial Intelligence (AI) tools are increasingly employed in diverse real-world applications, there has been significant interest in regulating these tools. To this end, several regulatory frameworks have been introduced by different countries worldwide. For example, the European Union recently passed the AI Act, the White House issued an Executive Order on safe, secure, and trustworthy AI, and the White House Office of Science and Technology Policy issued the Blueprint for an AI Bill of Rights (AI BoR). Many of these frameworks emphasize the need for auditing and improving the trustworthiness of AI tools, underscoring the importance of safety, privacy, explainability, fairness, and human fallback options. Although these regulatory frameworks highlight the necessity of enforcement, practitioners often lack detailed guidance on implementing them. Furthermore, the extensive research on operationalizing each of these aspects is frequently buried in technical papers that are difficult for practitioners to parse. In this write-up, we address this shortcoming by providing an accessible overview of existing literature related to operationalizing regulatory principles. We provide easy-to-understand summaries of state-of-the-art literature and highlight various gaps that exist between regulatory guidelines and existing AI research, including the trade-offs that emerge during operationalization. We hope that this work not only serves as a starting point for practitioners interested in learning more about operationalizing the regulatory guidelines outlined in the Blueprint for an AI BoR but also provides researchers with a list of critical open problems and gaps between regulations and state-of-the-art AI research. Finally, we note that this is a working paper and we invite feedback in line with the purpose of this document as described in the introduction.

CLIP embeddings have demonstrated remarkable performance across a wide range of computer vision tasks. However, these high-dimensional, dense vector representations are not easily interpretable, restricting their usefulness in downstream applications that require transparency. In this work, we empirically show that CLIP's latent space is highly structured, and consequently that CLIP representations can be decomposed into their underlying semantic components. We leverage this understanding to propose a novel method, Sparse Linear Concept Embeddings (SpLiCE), for transforming CLIP representations into sparse linear combinations of human-interpretable concepts. Distinct from previous work, SpLiCE does not require concept labels and can be applied post hoc. Through extensive experimentation with multiple real-world datasets, we validate that the representations output by SpLiCE can explain and even replace traditional dense CLIP representations, maintaining equivalent downstream performance while significantly improving their interpretability. We also demonstrate several use cases of SpLiCE representations including detecting spurious correlations, model editing, and quantifying semantic shifts in datasets.

With the increased deployment of machine learning models in various real-world applications, researchers and practitioners alike have emphasized the need for explanations of model behaviour. To this end, two broad strategies have been outlined in prior literature to explain models. Post hoc explanation methods explain the behaviour of complex black-box models by highlighting features that are critical to model predictions; however, prior work has shown that these explanations may not be faithful, and even more concerning is our inability to verify them. Specifically, it is nontrivial to evaluate if a given attribution is correct with respect to the underlying model. Inherently interpretable models, on the other hand, circumvent these issues by explicitly encoding explanations into model architecture, meaning their explanations are naturally faithful and verifiable, but they often exhibit poor predictive performance due to their limited expressive power. In this work, we aim to bridge the gap between the aforementioned strategies by proposing Verifiability Tuning (VerT), a method that transforms black-box models into models that naturally yield faithful and verifiable feature attributions. We begin by introducing a formal theoretical framework to understand verifiability and show that attributions produced by standard models cannot be verified. We then leverage this framework to propose a method to build verifiable models and feature attributions out of fully trained black-box models. Finally, we perform extensive experiments on semi-synthetic and real-world datasets, and show that VerT produces models that (1) yield explanations that are correct and verifiable and (2) are faithful to the original black-box models they are meant to explain.

Vision-language (VL) pretrained models have achieved impressive performance on multimodal reasoning and zero-shot recognition tasks. Many of these VL models are pretrained on unlabeled image and caption pairs from the internet. In this paper, we study whether representations of primitive concepts--such as colors, shapes, or the attributes of object parts--emerge automatically within these pretrained VL models. We propose a two-step framework, Compositional Concept Mapping (CompMap), to investigate this. CompMap first asks a VL model to generate primitive concept activations with text prompts, and then learns to construct a composition model that maps the primitive concept activations (e.g. the likelihood of black tail or red wing) to composite concepts (e.g. a red-winged blackbird). We show that a composition model can be reliably learn from ground truth primitive concepts. We thus hypothesize that if primitive concepts indeed emerge in a VL pretrained model, its primitive concept activations can be used to learn a composition model similar to the one designed by experts. We propose a quantitative metric to measure the degree of similarity, and refer to the metric as the interpretability metric. We also measure the classification accuracy when using the primitive concept activations and the learned composition model to predict the composite concepts, and refer to it as the usefulness metric. Our study reveals that state-of-the-art VL pretrained models learn primitive concepts that are highly useful for fine-grained visual recognition on the CUB dataset, and compositional generalization tasks on the MIT-States dataset. However, we observe that the learned composition models have low interpretability in our qualitative analyses. Our results reveal the limitations of existing VL models, and the necessity of pretraining objectives that encourage the acquisition of primitive concepts.