INDEX

Explanations

geographic features and locations

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

 Deckel

-0.39

 Decorations

-0.39

stoff

-0.36

älde

-0.36

 contesta

-0.36

テンツ

-0.35

 Declaration

-0.35

 Tahiti

-0.34

assorted

-0.34

 NUKAT

-0.34

POSITIVE LOGITS

tagHelperRunner

0.57

">//

0.50

 autorytatywna

0.47

 surrounded

0.46

ppur

0.45

XmlAccessorType

0.43

 surrounding

0.43

 CreateTagHelper

0.43

 inner

0.41

 occupies

0.41

Activations Density 0.314%

geographic features and locations

No Comments

No Known Activations