INDEX

Explanations

quantities and varieties of evidence or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tartalomajánló

-0.87

 <<<<<<<<<<<<<<

-0.83

msgTypes

-0.82

 AppComponent

-0.81

tonode

-0.81

 ModelExpression

-0.80

ConstraintMaker

-0.78

 contextLoads

-0.76

dersfield

-0.75

 Possession

-0.74

POSITIVE LOGITS

 there

0.89

 هناك

0.63

in

0.63

 behind

0.61

 There

0.61

there

0.60

десь

0.59

 CreateTagHelper

0.59

 here

0.59

 about

0.58

Activations Density 0.458%

quantities and varieties of evidence or information

No Comments

No Known Activations