INDEX

Explanations

proper nouns related to names and places

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

cho

-0.35

cho

-0.33

chor

-0.33

mock

-0.33

clic

-0.30

nearest

-0.30

bud

-0.30

<em>

-0.30

 Genes

-0.30

เก

-0.30

POSITIVE LOGITS

 estekak

0.70

 Administrativna

0.66

 betweenstory

0.65

الحياه

0.63

 мәкал

0.61

NewUrlParser

0.59

 فريبيس

0.58

 שוליים

0.58

 Chwiliwch

0.57

">//

0.57

Activations Density 0.151%

proper nouns related to names and places

No Comments

No Known Activations