INDEX

Explanations

forms of personal identification and associated details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ValueStyle

-0.71

 مشين

-0.60

LookAnd

-0.48

名

-0.47

 ویکی‌پدیا

-0.46

 danh

-0.46

EndTag

-0.45

mbad

-0.43

Preco

-0.42

 tủ

-0.41

POSITIVE LOGITS

 birth

0.74

ніципалі

0.69

Zip

0.65

VIAF

0.64

zip

0.63

 оригіналу

0.62

 사업

0.62

 Birth

0.61

webElementXpaths

0.60

 Phone

0.57

Activations Density 0.132%

forms of personal identification and associated details

No Comments

No Known Activations