INDEX

Explanations

mentions of the word "every" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

Espèce

-0.36

şört

-0.36

 Numerade

-0.36

recrow

-0.35

eningrad

-0.35

piecze

-0.33

出版年

-0.33

LOAT

-0.33

enguaje

-0.32

 asla

-0.32

POSITIVE LOGITS

 single

1.00

every

0.99

Every

0.89

 Every

0.85

 every

0.80

single

0.79

 eneste

0.77

 einzelne

0.76

 SINGLE

0.73

 singola

0.72

Activations Density 0.095%

mentions of the word "every" and its variations

No Comments

No Known Activations