INDEX

Explanations

code snippets or programming-related elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

rungsseite

-0.86

])))

-0.81

expandindo

-0.79

ंदीखरीदारी

-0.78

Demografia

-0.73

tagHelperRunner

-0.72

fjspx

-0.72

)))))

-0.71

)))),

-0.70

 parseFrom

-0.68

POSITIVE LOGITS

WillAppear

0.60

!("{

0.60

monial

0.56

enumi

0.55

—

0.54

//

0.51

illary

0.50

 مؤرشف

0.49

icious

0.49

\{\

0.49

Activations Density 0.071%

code snippets or programming-related elements

No Comments

No Known Activations