INDEX

Explanations

articles and determiners

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ی

-0.61

\{\\

-0.60

Autoritní

-0.57

}}}

-0.57

 cref

-0.56

tableFuture

-0.56

 StatusCode

-0.54

 Valera

-0.52

GINIA

-0.52

]?.

-0.52

POSITIVE LOGITS

an

0.94

An

0.67

 nouvel

0.65

 atque

0.65

An

0.61

την

0.59

manned

0.57

an

0.56

AN

0.55

 powerful

0.53

Activations Density 0.250%

articles and determiners

No Comments

No Known Activations