INDEX

Explanations

markings related to emphasis and unique characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 فريبيس

-0.62

 kaynağından

-0.59

due

-0.56

DoubleQuotes

-0.56

due

-0.55

AndEndTag

-0.52

 CreateTagHelper

-0.51

 devido

-0.49

GeneratedCode

-0.46

 vanwege

-0.45

POSITIVE LOGITS

 StatefulWidget

0.76

 <<<<<<<<<<<<<<

0.69

 automatiquement

0.68

 automáticamente

0.65

)]:

0.61

}(),

0.59

 StatelessWidget

0.59

 nakalista

0.59



0.58

日閲覧

0.58

Activations Density 0.661%

markings related to emphasis and unique characteristics

No Comments

No Known Activations