INDEX

Explanations

terms and phrases related to numerical data and computation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

出版年

-0.82

,:),

-0.68

 '\\;'

-0.68

endpush

-0.63

 Riches

-0.61

 kaynağından

-0.61

 للمعارف

-0.60

">:

-0.59

nyk

-0.58

 ámbitos

-0.58

POSITIVE LOGITS

 number

0.76

IntegerField

0.62

+#+#

0.61

исленность

0.60

 Number

0.59

 NUMBER

0.58

int

0.56

number

0.56

strconv

0.55

awtextra

0.54

Activations Density 0.300%

terms and phrases related to numerical data and computation

No Comments

No Known Activations