INDEX

Explanations

words related to a specific location or entity

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

 تضيفلها

-0.45

脚注の使い方

-0.45

Sans

-0.40

arbit

-0.40

 Manif

-0.40

ukone

-0.39

 Horn

-0.39

rem

-0.39

 extr

-0.37

Ams

-0.37

POSITIVE LOGITS

ftagPool

0.52

 vectorielles

0.52

ähteet

0.48

 vectorielle

0.47

 desmotivaciones

0.46

PostInfinity

0.46

tymologie

0.46

 enfans

0.46

 propOrder

0.45

 avoient

0.45

Activations Density 0.059%

words related to a specific location or entity

No Comments

No Known Activations