INDEX

Explanations

phrases about doubts and reasonable doubt, especially in legal contexts

oai_token-act-pair · gemini-2.0-flash

legal context

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 uncertainty

-1.80

 Uncertainty

-1.74

Uncertainty

-1.70

 doubt

-1.65

 uncertainties

-1.63

uncertainty

-1.62

 uncertain

-1.59

 Uncertain

-1.57

 doubts

-1.55

 doubtful

-1.48

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.63

LookAnd

0.55

 Bronze

0.55

出版年

0.55

CodeAnalysis

0.51

onded

0.51

 SqlCommand

0.50

 Richland

0.48

 bronze

0.47

 Villanueva

0.47

Activations Density 2.617%

phrases about doubts and reasonable doubt, especially in legal contexts

legal context

No Comments

No Known Activations