|
pulsatrix 1.1.0
|
Attribution graphs in the JSON that Neuronpedia's graph viewer and circuit-tracer's local viewer read (VIZ-4): nodes on a layer by token-position grid, and weighted links between them. More...
#include <cstdint>#include <optional>#include <string>#include <string_view>#include <vector>#include "pulsatrix/viz/document.hpp"

Go to the source code of this file.
Classes | |
| struct | pulsatrix::AttributionGraph |
An attribution graph as Neuronpedia's schema (graph-schema.json) and circuit-tracer's create_graph_files describe it. More... | |
| struct | pulsatrix::AttributionGraph::Node |
| struct | pulsatrix::AttributionGraph::Link |
Namespaces | |
| namespace | pulsatrix |
Functions | |
| std::string | pulsatrix::ToNeuronpediaJson (const AttributionGraph &graph) |
The graph as Neuronpedia/circuit-tracer JSON, including circuit-tracer's optional node fields (token_prob, is_target_logit) and an empty qParams. | |
| AttributionGraph | pulsatrix::ParseNeuronpediaGraph (std::string_view json) |
| Reads a graph written by ToNeuronpediaJson, circuit-tracer or Neuronpedia. Unknown fields are ignored. | |
| void | pulsatrix::ComputeInfluence (AttributionGraph &graph, const std::vector< double > &scores) |
| Sets each node's influence the way circuit-tracer's pruning does: nodes other than embeddings and logits, by |score| largest first, get the cumulative fraction of the total |score| up to and including them. The viewer keeps nodes whose influence is at most its threshold, so a threshold of 0.8 keeps the fewest nodes holding 80% of the score. | |
| void | pulsatrix::PruneLinks (AttributionGraph &graph, double edge_threshold) |
Keeps the fewest links, largest |weight| first, whose |weight| sums to at least edge_threshold of the total; ties keep their order. Links into a logit node are always kept. | |
| AttributionGraph | pulsatrix::FromCircuitGraph (const CircuitGraphDocument &doc, const std::string &slug, const std::string &scan) |
A circuit graph (a chain of operations scored by ablation) for the viewer: two columns, "input" holding an embedding node and "network" holding each operation one layer up, with the last operation as the output. Influence comes from the ablation effects. | |
Attribution graphs in the JSON that Neuronpedia's graph viewer and circuit-tracer's local viewer read (VIZ-4): nodes on a layer by token-position grid, and weighted links between them.