We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The use of transformer-based models is growing rapidly throughout society. With this growth, it is important to understand how they work, and in particular, how the attention mechanisms represent concepts. Though there are many interpretability methods, many look at models through their neuronal activations, which are poorly understood. We describe different lenses through which to view neuron activations, and investigate the effectiveness in language models and vision transformers through various methods of neural ablation: zero ablation, mean ablation, activation resampling, and a novel approach we term 'peak ablation'. Through experimental analysis, we find that in different regimes and models, each method can offer the lowest degradation of model performance compared to other methods, with resampling usually causing the most significant performance deterioration. We make our code available at https://github.com/nickypro/investigating-ablation.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2408.17322")
get_code_for_paper("2408.17322")
have("2408.17322")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2408.17322.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2408.17322)
Connect an agent — have() is free.