Automatically Interpreting Millions of Features in Large Language Models

• URL: http://arxiv.org/abs/2410.13928v1
• Date: Thu, 17 Oct 2024 17:56:01 GMT
• Title: Automatically Interpreting Millions of Features in Large Language Models
• Authors: Gonçalo Paulo, Alex Mallen, Caden Juang, Nora Belrose,
• Abstract summary: sparse autoencoders (SAEs) can be used to transform activations into a higher-dimensional latent space. We build an open-source pipeline to generate and evaluate natural language explanations for SAE features. Our large-scale analysis confirms that SAE latents are indeed much more interpretable than neurons.
• Score: 1.8035046415192353
• License:
• Abstract: While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which may be more easily interpretable. However, these SAEs can have millions of distinct latent features, making it infeasible for humans to manually interpret each one. In this work, we build an open-source automated pipeline to generate and evaluate natural language explanations for SAE features using LLMs. We test our framework on SAEs of varying sizes, activation functions, and losses, trained on two different open-weight LLMs. We introduce five new techniques to score the quality of explanations that are cheaper to run than the previous state of the art. One of these techniques, intervention scoring, evaluates the interpretability of the effects of intervening on a feature, which we find explains features that are not recalled by existing methods. We propose guidelines for generating better explanations that remain valid for a broader set of activating contexts, and discuss pitfalls with existing scoring techniques. We use our explanations to measure the semantic similarity of independently trained SAEs, and find that SAEs trained on nearby layers of the residual stream are highly similar. Our large-scale analysis confirms that SAE latents are indeed much more interpretable than neurons, even when neurons are sparsified using top-$k$ postprocessing. Our code is available at https://github.com/EleutherAI/sae-auto-interp, and our explanations are available at https://huggingface.co/datasets/EleutherAI/auto_interp_explanations.

Related papers

• Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning [4.051777802443125]
  Sparse Autoencoders (SAEs) are a promising approach for extracting neural network representations. We introduce Gradient SAEs, which modify the $k$-sparse autoencoder architecture by augmenting the TopK activation function. We find evidence that g-SAEs learn latents that are on average more effective at steering models in arbitrary contexts.
  arXiv  Detail & Related papers  (2024-11-15T18:03:52Z)
• Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders [115.34050914216665]
  Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for extracting sparse representations from language models. We introduce a suite of 256 SAEs, trained on each layer and sublayer of the Llama-3.1-8B-Base model, with 32K and 128K features. We assess the generalizability of SAEs trained on base models to longer contexts and fine-tuned models.
  arXiv  Detail & Related papers  (2024-10-27T17:33:49Z)
• Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs [0.0]
  We present an information-theoretic framework for interpreting SAEs as lossy compression algorithms. We argue that using MDL rather than sparsity may avoid potential pitfalls with naively maximising sparsity.
  arXiv  Detail & Related papers  (2024-10-15T01:38:03Z)
• Disentangling Dense Embeddings with Sparse Autoencoders [0.0]
  Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models. We show that the resulting sparse representations maintain semantic fidelity while offering interpretability.
  arXiv  Detail & Related papers  (2024-08-01T15:46:22Z)
• Interpreting Attention Layer Outputs with Sparse Autoencoders [3.201633659481912]
  Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. In this work we train SAEs on attention layer outputs and show that also here SAEs find a sparse, interpretable decomposition. We show that Sparse Autoencoders are a useful tool that enable researchers to explain model behavior in greater detail than prior work.
  arXiv  Detail & Related papers  (2024-06-25T17:43:13Z)
• Sparse Autoencoders Find Highly Interpretable Features in Language Models [0.0]
  Polysemanticity prevents us from identifying concise, human-understandable explanations for what neural networks are doing internally. We use sparse autoencoders to reconstruct the internal activations of a language model. Our method may serve as a foundation for future mechanistic interpretability work.
  arXiv  Detail & Related papers  (2023-09-15T17:56:55Z)
• FIND: A Function Description Benchmark for Evaluating Interpretability Methods [86.80718559904854]
  This paper introduces FIND (Function INterpretation and Description), a benchmark suite for evaluating automated interpretability methods. FIND contains functions that resemble components of trained neural networks, and accompanying descriptions of the kind we seek to generate. We evaluate methods that use pretrained language models to produce descriptions of function behavior in natural language and code.
  arXiv  Detail & Related papers  (2023-09-07T17:47:26Z)
• Interpretability at Scale: Identifying Causal Mechanisms in Alpaca [62.65877150123775]
  We use Boundless DAS to efficiently search for interpretable causal structure in large language models while they follow instructions. Our findings mark a first step toward faithfully understanding the inner-workings of our ever-growing and most widely deployed language models.
  arXiv  Detail & Related papers  (2023-05-15T17:15:40Z)
• Language Model Pre-Training with Sparse Latent Typing [66.75786739499604]
  We propose a new pre-training objective, Sparse Latent Typing, which enables the model to sparsely extract sentence-level keywords with diverse latent types. Experimental results show that our model is able to learn interpretable latent type categories in a self-supervised manner without using any external knowledge.
  arXiv  Detail & Related papers  (2022-10-23T00:37:08Z)
• Preliminary study on using vector quantization latent spaces for TTS/VC systems with consistent performance [55.10864476206503]
  We investigate the use of quantized vectors to model the latent linguistic embedding. By enforcing different policies over the latent spaces in the training, we are able to obtain a latent linguistic embedding. Our experiments show that the voice cloning system built with vector quantization has only a small degradation in terms of perceptive evaluations.
  arXiv  Detail & Related papers  (2021-06-25T07:51:35Z)
• Leveraging Sparse Linear Layers for Debuggable Deep Networks [86.94586860037049]
  We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. The resulting sparse explanations can help to identify spurious correlations, explain misclassifications, and diagnose model biases in vision and language tasks.
  arXiv  Detail & Related papers  (2021-05-11T08:15:25Z)

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.