United States

Sparse autoencoders (SAEs) are an unsupervised method for learning a sparse decomposition of a neural network’s latent representations into seemingly interpretable features. Despite recent excitement about their potential, research applications outside of industry are limited by the high cost of training a comprehensive suite of SAEs. In this work, we introduce Gemma Scope, an open suite of JumpReLU SAEs trained on all layers and sub-layers of Gemma 2 2B and 9B and select layers of Gemma 2 27B base models. We primarily train SAEs on the Gemma 2 pre-trained models, but additionally release SAEs trained on instruction-tuned Gemma 2 9B for comparison. We evaluate the quality of each SAE on standard metrics and release these results. We hope that by releasing these SAE weights, we can help make more ambitious safety and interpretability research easier for the community. Weights and a tutorial can be found at https://huggingface.co/google/gemma-scope and an interactive demo can be found at https://neuronpedia.org/gemma-scope.

EMNLP 2024

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

open weights

sparse autoencoders

interpretability

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

Transformer-based language models have shown an excellent ability to effectively cap- ture and utilize contextual information. Al- though various analysis techniques have been used to quantify and trace the contribution of single contextual cues to a target task such as subject-verb agreement or coreference resolu- tion, scenarios in which multiple relevant cues are available in the context remain underex- plored. In this paper, we investigate how lan- guage models handle gender agreement when multiple gender cue words are present, each capable of independently disambiguating a tar- get gender pronoun. We analyze two widely used Transformer-based models: BERT, an encoder-based, and GPT-2, a decoder-based model. Our analysis employs two comple- mentary approaches: context mixing analysis, which tracks information flow within the model, and a variant of activation patching, which mea- sures the impact of cues on the model’s predic- tion. We find that BERT tends to prioritize the first cue in the context to form both the target word representations and the model’s predic- tion, while GPT-2 relies more on the final cue. Our findings reveal striking differences in how encoder-based and decoder-based models pri- oritize and use contextual information for their predictions.

How Language Models Prioritize Contextual Grammatical Cues?

Despite the widespread adoption of autoregressive language models, explainability evaluation research has predominantly focused on span infilling and masked language models. Evaluating the faithfulness of an explanation method—how accurately it explains the inner workings and decision-making of the model—is challenging because it is difficult to separate the model from its explanation. Most faithfulness evaluation techniques corrupt or remove input tokens deemed important by a particular attribution (feature importance) method and observe the resulting change in the model's output. However, for autoregressive language models, this approach creates out-of-distribution inputs due to their next-token prediction training objective. In this study, we propose a technique that leverages counterfactual generation to evaluate the faithfulness of attribution methods for autoregressive language models. Our technique generates fluent, in-distribution counterfactuals, making the evaluation protocol more reliable.

Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models

Sparse AutoEncoders (SAEs) have gained popularity as a tool for enhancing the interpretability of Large Language Models (LLMs). However, training SAEs can be computationally intensive, especially as model complexity grows. In this study, the potential of transfer learning to accelerate SAEs training is explored by capitalizing on the shared representations found across adjacent layers of LLMs. Our experimental results demonstrate that fine-tuning SAEs using pre-trained models from nearby layers not only maintains but often improves the quality of learned representations, while significantly accelerating convergence. These findings indicate that the strategic reuse of pretrained SAEs is a promising approach, particularly in settings where computational resources are constrained.

Accelerating Sparse Autoencoder Training via Layer-Wise Transfer Learning in Large Language Models

Enriching Conceptual Knowledge in Language Models through Metaphorical Reference Explanation

Polish Coreference Corpus as an LLM Testbed: Evaluating Coreference Resolution within Instruction-Following Language Models by Instruction-Answer Alignment

MSCAW-coref: Multilingual, Singleton and Conjunction-Aware Word-Level Coreference Resolution

Unifying the Scope of Bridging Anaphora Types in English: Bridging Annotations in ARRAU and GUM

While measuring bias and robustness in coreference resolution are important goals, such measurements are only as good as the tools we use to measure them. Winogender Schemas (Rudinger et al., 2018) are an influential dataset proposed to evaluate gender bias in coreference resolution, but a closer look reveals issues with the data that compromise its use for reliable evaluation, including treating different pronominal forms as equivalent, violations of template constraints, and typographical errors. We identify these issues and fix them, contributing a new dataset: WinoPron. Using WinoPron, we evaluate two state-of-the-art supervised coreference resolution systems, SpanBERT, and five sizes of FLAN-T5, and demonstrate that accusative pronouns are harder to resolve for all models. We also propose a new method to evaluate pronominal bias in coreference resolution that goes beyond the binary. With this method, we also show that bias characteristics vary not just across pronoun sets (e.g., he vs. she), but also across surface forms of those sets (e.g., him vs. his).

WinoPron: Revisiting English Winogender Schemas for Consistency, Coverage, and Grammatical Case

Coreference Resolution is the process of detecting a cluster of mentions that point to the same entity. This paper presents the Coreference Resolution system for Hindi based on Bi-GRU-CNN and Biaffine classifier with IndicBERT and MuRIL BERT. The motivation behind this work is the scarcity of resources available for Hindi and to diminish the dependency on the external parser and hand-crafted feature used by the previous Coreference resolution model in the Hindi language. The coreference annotated dataset is used for the Hindi language, containing 3.6K verbalizations and 78K tokens from the news article domain. The experimental results received are promising in the form of Precision, Recall, and F-measure.

Downloads

Next from EMNLP 2024

How Language Models Prioritize Contextual Grammatical Cues?

Similar lecture

Accelerating Sparse Autoencoder Training via Layer-Wise Transfer Learning in Large Language Models

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EMNLP 2024

How Language Models Prioritize Contextual Grammatical Cues?

Similar lecture

Accelerating Sparse Autoencoder Training via Layer-Wise Transfer Learning in Large Language Models

Downloads