INDEX

Explanations

references to individuals, organizations, or ideologies in the context of governance or social structure

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

STC

-0.78

 Candel

-0.78

THON

-0.77

XS

-0.73

 Jarrett

-0.72

Zach

-0.71

 Protest

-0.70

 Zach

-0.69

WebVitals

-0.69

 пом

-0.69

POSITIVE LOGITS

ض

0.77

);?>

0.76

NewUrlParser

0.71

;?>

0.70

apollo

0.70

</h6>

0.70

Datuak

0.69

 nawr

0.69

]}"

0.67

 Freeman

0.66

Activations Density 2.694%

references to individuals, organizations, or ideologies in the context of governance or social structure

No Comments

No Known Activations