INDEX

Explanations

terms related to internet culture and online anonymity

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

AxisAlignment

-0.97

__':

-0.88

__":

-0.84

 Audiodateien

-0.84

__":

-0.83

reportWebVitals

-0.82

 HasFactory

-0.82

 estekak

-0.79

</caption>

-0.77

 numberOfRows

-0.76

POSITIVE LOGITS

 bullshit

0.68

WTF

0.67

 noob

0.67

 Awesome

0.67

WTF

0.66

 badass

0.64

esomeness

0.64

Derp

0.63

 memes

0.63

 hater

0.62

Activations Density 0.500%

terms related to internet culture and online anonymity

No Comments

No Known Activations