INDEX

Explanations

elements related to technical specifications or coding constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 تضيفلها

-0.79

QMetaType

-0.78

 contextLoads

-0.74

Digitized

-0.71

($__

-0.70

 lenker

-0.70

IntoConstraints

-0.68

 ProtoMessage

-0.68

 BoxFit

-0.67

GeoNames

-0.64

POSITIVE LOGITS

//

1.25

///

1.01

[toxicity=0]

0.98

//*

0.86

//

0.82

0.76

////

0.76

/*

0.75

());//

0.75

 infância

0.75

Activations Density 0.055%

elements related to technical specifications or coding constructs

No Comments

No Known Activations