Javier Ferrando, Elena Voita
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.
Information flows by routes inside the network via mechanisms implemented in the model. These routes can be represented as graphs where nodes correspond to token representations and edges to computations. We automatically build these graphs in a top-down manner, for each prediction leaving only the most important nodes and edges. In contrast to the existing workflows relying on activation patching, we do this through attribution: this allows us to efficiently uncover existing circuits with just a single forward pass. Unlike with patching, we do not need a human to carefully design prediction templates, and we can extract information flow routes for any prediction (not just the ones among the allowed templates). As a result, we can analyze model behavior in general, for specific types of predictions, or different domains. We experiment with Llama 2 and show that some attention head roles are overall important, e.g. previous token heads and subword merging heads. Next, we find similarities in Llama 2 behavior when handling tokens of the same part of speech. Finally, we show that some model components can be specialized on domains such as coding or multilingual texts.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.00824")
get_code_for_paper("2403.00824")
have("2403.00824")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2403.00824.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2403.00824)
Connect an agent — have() is free.