INDEX

Explanations

references to professional wrestling and related storylines

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rophes

-0.56

 trúc

-0.52

 colegios

-0.50

 виправивши

-0.50

geving

-0.50

 Rover

-0.48

fur

-0.47

一说

-0.47

akes

-0.47

soby

-0.46

POSITIVE LOGITS

WWE

1.11

WWE

0.96

 wrestling

0.84

 Wrestling

0.84

 wrestler

0.84

 wrestlers

0.83

Wrestling

0.81

 WrestleMania

0.81

wwe

0.80

 backstage

0.76

Activations Density 0.088%

references to professional wrestling and related storylines

No Comments

No Known Activations