Related papers: Low-Rank Adapting Models for Sparse Autoencoders

Low-Rank Adapting Models for Sparse Autoencoders

URL: http://arxiv.org/abs/2501.19406v1
Date: Fri, 31 Jan 2025 18:59:16 GMT
Title: Low-Rank Adapting Models for Sparse Autoencoders
Authors: Matthew Chen, Joshua Engels, Max Tegmark,
Abstract summary: We use low-rank adaptation (LoRA) to finetune the language model itself around a previously trained SAE. We analyze our method across SAE sparsity, SAE width, language model size, LoRA rank, and model layer on the Gemma Scope family of SAEs.
Score: 6.932760557251821
License:
Abstract: Sparse autoencoders (SAEs) decompose language model representations into a sparse set of linear latent vectors. Recent works have improved SAEs using language model gradients, but these techniques require many expensive backward passes during training and still cause a significant increase in cross entropy loss when SAE reconstructions are inserted into the model. In this work, we improve on these limitations by taking a fundamentally different approach: we use low-rank adaptation (LoRA) to finetune the language model itself around a previously trained SAE. We analyze our method across SAE sparsity, SAE width, language model size, LoRA rank, and model layer on the Gemma Scope family of SAEs. In these settings, our method reduces the cross entropy loss gap by 30% to 55% when SAEs are inserted during the forward pass. We also find that compared to end-to-end (e2e) SAEs, our approach achieves the same downstream cross entropy loss 3$\times$ to 20$\times$ faster on Gemma-2-2B and 2$\times$ to 10$\times$ faster on Llama-3.2-1B. We further show that our technique improves downstream metrics and can adapt multiple SAEs at once. Our results demonstrate that improving model interpretability is not limited to post-hoc SAE training; Pareto improvements can also be achieved by directly optimizing the model itself.

Related papers

Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
Large language models (LLMs) have significantly improved language understanding and generation capabilities. LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands. We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
arXiv Detail & Related papers (2024-12-19T18:08:04Z)
How to Learn a New Language? An Efficient Solution for Self-Supervised Learning Models Unseen Languages Adaption in Low-Resource Scenario [72.02391485962127]
Speech Self-Supervised Learning (SSL) models achieve impressive performance on Automatic Speech Recognition (ASR) In low-resource language ASR, they encounter the domain mismatch problem between pre-trained and low-resource languages. We extend a conventional efficient fine-tuning scheme based on the adapter to handle these issues.
arXiv Detail & Related papers (2024-11-27T10:51:00Z)
Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups [0.0]
We propose a novel training strategy that reduces the number of trained SAEs from one per layer to one for a given group of contiguous layers. Our experimental results on Pythia 160M highlight a speedup of up to 6x without compromising the reconstruction quality and performance on downstream tasks.
arXiv Detail & Related papers (2024-10-28T20:23:30Z)
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)
Pruning Large Language Models with Semi-Structural Adaptive Sparse Training [17.381160429641316]
Adaptive Sparse Trainer (AST) is a novel and efficient retraining framework tailored for semi-structured sparse models. AST reduces the perplexity and zero-shot accuracy gap between dense and 2:4 semi-structured sparse models to 0.6 and 1.16%, respectively.
arXiv Detail & Related papers (2024-07-30T06:33:44Z)
Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning [52.29522018586365]
We study structured pruning as an effective means to develop smaller LLMs from pre-trained, larger models. Our approach employs two key techniques: (1) targeted structured pruning, which prunes a larger model to a specified target shape by removing layers, heads, and intermediate and hidden dimensions in an end-to-end manner, and (2) dynamic batch loading, which dynamically updates the composition of sampled data in each training batch based on varying losses across different domains.
arXiv Detail & Related papers (2023-10-10T15:13:30Z)
Fine-Tuning Language Models with Just Forward Passes [92.04219196752007]
Fine-tuning language models (LMs) has yielded success on diverse downstream tasks, but as LMs grow in size, backpropagation requires a large amount of memory. We propose a memory-efficient zerothorder (MeZO) to operate in-place, thereby fine-tuning LMs with the same memory footprint as inference.
arXiv Detail & Related papers (2023-05-27T02:28:10Z)
Lipreading using Temporal Convolutional Networks [57.41253104365274]
Current model for recognition of isolated words in-the-wild consists of a residual network and Bi-directional Gated Recurrent Unit layers. We address the limitations of this model and we propose changes which further improve its performance. Our proposed model results in an absolute improvement of 1.2% and 3.2%, respectively, in these datasets.
arXiv Detail & Related papers (2020-01-23T17:49:35Z)

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