INDEX

Explanations

numerical data and references, especially related to publications or scientific notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

TagMode

-0.90

invokeLater

-0.84

EndGlobalSection

-0.83

 >=",

-0.78

SourceChecksum

-0.76

tagHelperRunner

-0.71

SharedDtor

-0.70

RegressionTest

-0.70

 jsPsych

-0.70

oneofs

-0.69

POSITIVE LOGITS

ην

0.49

又是

0.49

дыду

0.45

#!/

0.45

同じく

0.43

 فريبيس

0.43

 برانيه

0.42

лактика

0.42

 kasarigan

0.41

ebe

0.40

Activations Density 3.576%

numerical data and references, especially related to publications or scientific notation

No Comments

No Known Activations