INDEX

Explanations

elements that highlight quality and features of products or services

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

 suatu

-0.34

StackNavigator

-0.34

 Ausgang

-0.33

 nôtre

-0.33

 malheur

-0.33

 kommunen

-0.32

 Brücke

-0.31

 Bibliothek

-0.30

 couvercle

-0.30

 thôi

-0.30

POSITIVE LOGITS

UnusedPrivate

0.72

 ویکی‌پدی

0.69

ViewFeatures

0.68

 nakalista

0.66

 BorderSide

0.65

Geplaatst

0.65

 للاسماء

0.65

GTCX

0.65

RefNanny

0.64

jspb

0.63

Activations Density 0.434%

elements that highlight quality and features of products or services

No Comments

No Known Activations