INDEX

Explanations

cooking instructions and ingredient-related actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

 فريبيس

-0.56

او

-0.52

oredCriteria

-0.50

setDefault

-0.48

मन

-0.46

󠁴

-0.45

 voisin

-0.44

 THEOD

-0.43

its

-0.42

 gede

-0.42

POSITIVE LOGITS

upuesto

0.66

/**

0.63

astronomie

0.61

μφωνα

0.61

 Conjug

0.60

MetaType

0.60

љено

0.59

 mergeFrom

0.59

 चीज़ों

0.59

 CascadeType

0.59

Activations Density 0.020%

cooking instructions and ingredient-related actions

No Comments

No Known Activations