|
pulsatrix 1.1.0
|
A language model's attribution graph from AttnLRP (VIZ-4): how relevance for one predicted token flows from the input tokens through every layer's residual stream, ready for Neuronpedia's and circuit-tracer's graph viewers. More...
#include <cstdint>#include <string>#include <vector>#include "pulsatrix/attnlrp_parity.hpp"#include "pulsatrix/causal_lm.hpp"#include "pulsatrix/lrp_rule_config.hpp"#include "pulsatrix/viz/attribution_graph.hpp"

Go to the source code of this file.
Classes | |
| struct | pulsatrix::RelevanceGraphOptions |
Namespaces | |
| namespace | pulsatrix |
Functions | |
| AttributionGraph | pulsatrix::BuildRelevanceGraph (CausalLM &model, DeviceBackend *backend, const std::vector< int64_t > &ids, int64_t target, const RelevanceGraphOptions &options) |
Explains the model's logit for target at the last position with LRP and returns the relevance flow as an attribution graph. | |
A language model's attribution graph from AttnLRP (VIZ-4): how relevance for one predicted token flows from the input tokens through every layer's residual stream, ready for Neuronpedia's and circuit-tracer's graph viewers.