Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Practical Pitfalls of Causal Scrubbing, published by Jérémy Scheurer on March 27, 2023 on The AI Alignment Forum.

TL;DR: We evaluate Causal Scrubbing (CaSc) on synthetic graphs with known ground truth to determine its reliability in confirming correct hypotheses and rejecting incorrect ones. First, we show that CaSc can accurately identify true hypotheses and quantify the degree to which a hypothesis is wrong. Second, we highlight some limitations of CaSc, in particular, that it cannot falsify all incorrect hypotheses. We provide concrete examples of false positive results with causal scrubbing. Our main finding is that false positives can occur when there is “cancellation”, i.e., CaSc causes the model to do better on some inputs and worse on others, such that, on average, the scrubbed model recovers the full loss. A second practical failure mode is that CaSc cannot detect whether a proposed hypothesis is specific enough, and it cannot distinguish between hypotheses that are extensionally equivalent.

We thank Redwood Research for generously supporting this project by providing us with their Causal Scrubbing implementation, access to REMIX materials, and computational resources. We specifically thank Ansh Radhakrishnan, Buck Shlegeris, and Nicholas Goldowsdky-Dill for their feedback and advice. We thank the Long-Term Future Fund for financial support and Marcel Steimke and Lennart Heim for operational support. Finally, we thank Marius Hobbhahn, Adam Jermyn, and Erik Jenner for valuable discussions and feedback.

Introduction

Causal Scrubbing (CaSc) is a method to evaluate the accuracy of hypotheses about neural networks and provides a measure of the deviation of a hypothesis from the ground truth. However, CaSc does not guarantee to reject false or incomplete hypotheses. We thus believe that systematic evaluation of CaSc to investigate these limitations is valuable (in addition to evaluating its effectiveness in the wild, as done in most existing work). Hence, we evaluate CaSc to highlight its strengths and weaknesses and explore the reliability of CaSc in confirming correct hypotheses and rejecting incorrect ones.

We evaluate the reliability of CaSc on synthetic graphs. While synthetic graphs are less realistic than trained neural networks, we get access to the known ground truth interpretation, which allows us to accurately evaluate our hypotheses. Since CaSc operates on general computational graphs, any results on synthetic graphs also apply to using CaSc on neural networks (although we don’t make any claim on how likely the situations we find are to occur in trained neural networks).

Our evaluation is based on creating a synthetic graph that solves a specific problem (e.g., sorting a list) and creating an identical interpretation graph (the correct hypothesis). We then perturb the correct interpretation graph to make the hypothesis “worse”. Finally, we evaluate whether CaSc correctly determines the better hypothesis. Ideally, we want the scrubbed loss (the loss induced by applying CaSc) to correlate with the “correctness” of a hypothesis.

To determine whether a hypothesis is “better” or “worse”, we introduce the concepts of extensional and intensional equivalence between functions. Extensional equivalent functions have the same input-output behavior; for example, Quicksort and Mergesort are extensionally equivalent as they both sort an input sequence. Intensional equivalent functions are implemented in the same way mechanistically. So once we zoom further in and compare Quicksort and Mergesort algorithmically, we see that they are not intensionally equivalent. This point is already made in the CaSc writeup, and our goal is merely to highlight that in the context of mechanistic interpretability, this is an important distinction that’s easy to overlook.

In this post,...