INDEX

Explanations

references to locations and geographic entities

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

hyrchwyd

-0.50

 betweenstory

-0.48

ähteet

-0.47

 vuestros

-0.43

featureID

-0.42

 będ

-0.42

<?

-0.41

 vuestro

-0.41

 appunto

-0.39

 AssemblyCulture

-0.39

POSITIVE LOGITS

arakhand

0.59

matchCondition

0.56

 junior

0.52

baga

0.50

citi

0.50

 Citizens

0.50

 Unis

0.50

 police

0.50

nior

0.49

cinnati

0.49

Activations Density 0.411%

references to locations and geographic entities

No Comments

No Known Activations