INDEX

Explanations

variations of the word "grease."

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

@[+][

-0.79

 MessageBoxIcon

-0.78

ValueStyle

-0.68

 totales

-0.63

tagext

-0.62

ImageContext

-0.60

 therefor

-0.57

 Nazar

-0.56

 thirst

-0.56

 eventId

-0.56

POSITIVE LOGITS

Gre

0.72

Gre

0.65

Nationalité

0.65

Fre

0.61

Fre

0.59

gre

0.58

</thead>

0.57

fre

0.56

FRE

0.51

Hav

0.51

Activations Density 0.064%

variations of the word "grease."

No Comments

No Known Activations