mirror of
https://github.com/elder-plinius/OBLITERATUS.git
synced 2026-05-11 11:37:49 +02:00
pliny
71 lines
2.8 KiB
Python
71 lines
2.8 KiB
Python
"""Novel analysis techniques for mechanistic interpretability of refusal."""
|
|
|
|
from obliteratus.analysis.cross_layer import CrossLayerAlignmentAnalyzer
|
|
from obliteratus.analysis.logit_lens import RefusalLogitLens
|
|
from obliteratus.analysis.whitened_svd import WhitenedSVDExtractor
|
|
from obliteratus.analysis.activation_probing import ActivationProbe
|
|
from obliteratus.analysis.defense_robustness import DefenseRobustnessEvaluator
|
|
from obliteratus.analysis.concept_geometry import ConceptConeAnalyzer
|
|
from obliteratus.analysis.alignment_imprint import AlignmentImprintDetector
|
|
from obliteratus.analysis.multi_token_position import MultiTokenPositionAnalyzer
|
|
from obliteratus.analysis.sparse_surgery import SparseDirectionSurgeon
|
|
from obliteratus.analysis.causal_tracing import CausalRefusalTracer
|
|
from obliteratus.analysis.residual_stream import ResidualStreamDecomposer
|
|
from obliteratus.analysis.probing_classifiers import LinearRefusalProbe
|
|
from obliteratus.analysis.cross_model_transfer import TransferAnalyzer
|
|
from obliteratus.analysis.steering_vectors import (
|
|
SteeringVectorFactory,
|
|
SteeringHookManager,
|
|
)
|
|
from obliteratus.analysis.sae_abliteration import (
|
|
SparseAutoencoder,
|
|
train_sae,
|
|
identify_refusal_features,
|
|
SAEDecompositionPipeline,
|
|
)
|
|
from obliteratus.analysis.tuned_lens import TunedLensTrainer, RefusalTunedLens
|
|
from obliteratus.analysis.riemannian_manifold import RiemannianManifoldAnalyzer
|
|
from obliteratus.analysis.anti_ouroboros import AntiOuroborosProber
|
|
from obliteratus.analysis.conditional_abliteration import ConditionalAbliterator
|
|
from obliteratus.analysis.wasserstein_transfer import WassersteinRefusalTransfer
|
|
from obliteratus.analysis.spectral_certification import (
|
|
SpectralCertifier,
|
|
CertificationLevel,
|
|
)
|
|
from obliteratus.analysis.activation_patching import ActivationPatcher
|
|
from obliteratus.analysis.wasserstein_optimal import WassersteinOptimalExtractor
|
|
from obliteratus.analysis.bayesian_kernel_projection import BayesianKernelProjection
|
|
|
|
__all__ = [
|
|
"CrossLayerAlignmentAnalyzer",
|
|
"RefusalLogitLens",
|
|
"WhitenedSVDExtractor",
|
|
"ActivationProbe",
|
|
"DefenseRobustnessEvaluator",
|
|
"ConceptConeAnalyzer",
|
|
"AlignmentImprintDetector",
|
|
"MultiTokenPositionAnalyzer",
|
|
"SparseDirectionSurgeon",
|
|
"CausalRefusalTracer",
|
|
"ResidualStreamDecomposer",
|
|
"LinearRefusalProbe",
|
|
"TransferAnalyzer",
|
|
"SteeringVectorFactory",
|
|
"SteeringHookManager",
|
|
"SparseAutoencoder",
|
|
"train_sae",
|
|
"identify_refusal_features",
|
|
"SAEDecompositionPipeline",
|
|
"TunedLensTrainer",
|
|
"RefusalTunedLens",
|
|
"RiemannianManifoldAnalyzer",
|
|
"AntiOuroborosProber",
|
|
"ConditionalAbliterator",
|
|
"WassersteinRefusalTransfer",
|
|
"SpectralCertifier",
|
|
"CertificationLevel",
|
|
"ActivationPatcher",
|
|
"WassersteinOptimalExtractor",
|
|
"BayesianKernelProjection",
|
|
]
|