INDEX

Explanations

proper nouns, particularly names associated with contributions or studies

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

Appears near or within names

np_acts-logits-general · gemini-2.0-flash

Chinese names and surnames

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isContained

-0.53

 ripar

-0.50

 ivelany

-0.49

 Mores

-0.48

RTLD

-0.46

topi

-0.46

 Ablauf

-0.45

 recom

-0.45

caled

-0.45

MLLoader

-0.45

POSITIVE LOGITS

NameInMap

0.77

sizeCache

0.76

 تضيفلها

0.74

 estekak

0.68

 NSCoder

0.66

Hentet

0.63

jsxFileName

0.62

 propOrder

0.61

expandindo

0.61

StructEnd

0.58

Activations Density 0.194%

proper nouns, particularly names associated with contributions or studies

Appears near or within names

Chinese names and surnames

No Comments

No Known Activations