INDEX

Explanations

numerical data points or values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

社の

-0.55

-0.49

 poros

-0.49

 desped

-0.48

dett

-0.46

 Quell

-0.45

 StatelessWidget

-0.45

各样的

-0.44

ICOLON

-0.44

ابت

-0.43

POSITIVE LOGITS

+#+#

0.87

tagHelperRunner

0.87

出版年

0.77

 itſelf

0.77

webElementGuid

0.76

 Diſ

0.74

 myſelf

0.72

<?

0.72

 useStyles

0.69

 ſeveral

0.69

Activations Density 0.312%

numerical data points or values

No Comments

No Known Activations