INDEX

Explanations

sections of text that contain programming or technical language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Vidite

-0.97

 للمعارف

-0.89

 Италијани

-0.80

EndContext

-0.75

ScopeManager

-0.73

 Italijanski

-0.66

elemField

-0.66

Portale

-0.65

IsContent

-0.65

//

-0.64

POSITIVE LOGITS

0.54

 others

0.53

 interest

0.53

 يتيمه

0.51

 مشين

0.48

0.47

 board

0.47

0.46

0.45

Activations Density 0.013%

sections of text that contain programming or technical language

No Comments

No Known Activations