INDEX

Explanations

formatted HTML references or entities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 يتيمه

-0.91

SourceChecksum

-0.84

LookAnd

-0.83

 transférez

-0.81

ArrowToggle

-0.78

fromnode

-0.78

kloped

-0.77

awtextra

-0.76

oa̍t

-0.71

 mergeFrom

-0.70

POSITIVE LOGITS

amp

1.73

 Hamp

0.79

AMP

0.78

amps

0.69

amp

0.69

Amp

0.68

aimana

0.64

#!/

0.58

Pip

0.55

Activations Density 0.053%

formatted HTML references or entities

No Comments

No Known Activations