INDEX

Explanations

phrases related to medical diagnostics and treatments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Obrador

-0.59

 épouse

-0.56

fvar

-0.55

DIT

-0.52

 InputDecoration

-0.49

 popolari

-0.47

 Komponist

-0.46

laceae

-0.46

 agreeable

-0.46

 mundane

-0.46

POSITIVE LOGITS

 expensive

0.82

 autorytatywna

0.78

 costly

0.71

 esternos

0.68

XmlAccessType

0.67

 Expensive

0.66

 pricey

0.65

expensive

0.64

 NSCoder

0.61

yntaxException

0.60

Activations Density 0.487%

phrases related to medical diagnostics and treatments

No Comments

No Known Activations