INDEX

Explanations

references to former officials or leaders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

otherwise

-0.51

 otherwise

-0.51

Otherwise

-0.50

tualmente

-0.50

 Otherwise

-0.49

 currently

-0.46

currently

-0.46

 atualmente

-0.44

 attualmente

-0.44

 Bewußt

-0.44

POSITIVE LOGITS

 Yugoslavia

0.75

 Yugoslav

0.66

 Soviet

0.63

 glories

0.60

 slaves

0.59

 USSR

0.59

 presidents

0.57

 Olympian

0.57

 soviet

0.56

KGB

0.56

Activations Density 0.166%

references to former officials or leaders

No Comments

No Known Activations