Mapping Mind Language Model

Mapping the Mind of a Large Language Model \ Anthropic Interpretability Mapping the Mind of a Large Language Model May 21, 2024 Read the paper

Today we report a significant advance in understanding the inner workings of AI models. We have identified how millions of concepts are represented inside Claude Sonnet, one of our deployed large language models. This is the first ever detailed look inside a modern, production-grade large language model. This interpretability discovery could, in future, help us make AI models safer.

We mostly treat AI models as a black box: something goes in and a response comes out, and it's not clear why the model gave that particular response instead of another. This makes it hard to trust that these models are safe: if we don't know how they work, how do we know they won't give harmful, biased, untruthful, or otherwise dangerous responses? How can we trust that they’ll be safe and reliable?

Opening the black box doesn't necessarily help: the internal state of the model—what the model is "thinking" before writing its response—consists of a long list of numbers ("neuron activations") without a clear meaning. From interacting with a model like Claude, it's clear that it’s able to understand and wield a wide range of concepts—but we can't discern them from looking directly at neurons. It turns out that each concept is represented across many neurons, and each neuron is involved in representing many concepts.

Previously, we made some progress matching patterns of neuron activations, called features, to human-interpretable concepts. We used a technique called "dictionary learning", borrowed from classical machine learning, which isolates patterns of neuron activations that recur across many different contexts. In turn, any internal state of the model can be represented in terms of a few active features instead of many active neurons. Just as every English word in a dictionary is made by combining letters, and every sentence is made by combining words, every feature in an AI model is made by combining neurons, and every internal state is made by combining features.

In October 2023, we reported success applying dictionary learning to a very small "toy" language model and found coherent features corresponding to concepts like uppercase text, DNA sequences, surnames in citations, nouns in mathematics, or function arguments in Python code.

Those concepts were intriguing—but the model really was very simple. Other researchers subsequently applied similar techniques to somewhat larger and more complex models than in our original study. But we were optimistic that we could scale up the technique to the vastly larger AI language models now in regular use, and in doing so, learn a great deal about the features supporting their sophisticated behaviors. This required going up by many orders of magnitude—from a backyard bottle rocket to a Saturn-V.

There was both an engineering challenge (the raw sizes of the models involved required heavy-duty parallel computation) and scientific risk (large models behave differently to small ones, so the same technique we used before might not have worked). Luckily, the engineering and scientific expertise we've developed training large language models for Claude actually transferred to helping us do these large dictionary learning experiments. We used the same scaling law philosophy that predicts the performance of larger models from smaller ones to tune our methods at an affordable scale before launching on Sonnet.

As for the scientific risk, the proof is in the pudding.

We successfully extracted millions of features from the middle layer of Claude 3.0 Sonnet, (a member of our current, state-of-the-art model family, currently available on claude.ai ), providing a rough conceptual map of its internal states halfway through its computation. This is the first ever detailed look inside a modern, production-grade large language model.

Whereas the features we found in the toy language model were rather superficial, the features we found in Sonnet have a depth, breadth, and abstraction reflecting Sonnet's advanced capabilities.

We see features corresponding to a vast range of entities like cities (San Francisco), people (Rosalind Franklin), atomic elements (Lithium), scientific fields (immunology), and programming syntax (function calls). These features are multimodal and multilingual, responding to images of a given entity as well as its name or description in many languages.

A feature sensitive to mentions of the Golden Gate Bridge fires on a range of model inputs, from English mentions of the name of the bridge to discussions in Japanese, Chinese, Greek, Vietnamese, Russian, and an image. The orange color denotes the words or word-parts on which the feature is active. We also find more abstract features—responding to things like bugs in computer code, discussions of gender bias in professions, and conversations about keeping secrets.

Three examples of features that activate on more abstract concepts: bugs in computer code, descriptions of gender bias in professions, and conversations about keeping secrets.

We were able to measure a kind of "distance" between features based on which neurons appeared in their activation patterns. This allowed us to look for features that are "close" to each other. Looking near a "Golden Gate Bridge" feature, we found features for Alcatraz Island, Ghirardelli Square, the Golden State Warriors, California Governor Gavin Newsom, the 1906 earthquake, and the San Francisco-set Alfred Hitchcock film Vertigo .

This holds at a higher level of conceptual abstraction: looking near a feature related to the concept of "inner conflict", we find features related to relationship breakups, conflicting allegiances, logical inconsistencies, as well as the phrase "catch-22". This shows that the internal organization of concepts in the AI model corresponds, at least somewhat, to our human notions of similarity. This might be the origin of Claude's excellent ability to make analogies and metaphors.

A map of the features near an "Inner Conflict" feature, including clusters related to balancing tradeoffs, romantic struggles, conflicting allegiances, and catch-22s. Importantly, we can also manipulate these features, artificially amplifying or suppressing them to see how Claude's responses change.

For example, amplifying the "Golden Gate Bridge" feature gave…