INDEX

Explanations

patterns related to nested structures or syntax in code or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ی

-0.61

zion

-0.57

 Reap

-0.55

 LANG

-0.53

arias

-0.53

zac

-0.53

 Mays

-0.53

ô

-0.52

zac

-0.52

Grath

-0.52

POSITIVE LOGITS

Datuak

1.00

 '\\;'

0.99

 mergeFrom

0.95

})

0.94

 مرئيه

0.92

))

0.92

 AssemblyTitle

0.90

])

0.89

ंदीखरीदारी

0.87

yntaxException

0.87

Activations Density 0.208%

patterns related to nested structures or syntax in code or markup languages

No Comments

No Known Activations