INDEX

Explanations

terms related to formal approvals and actions

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

HasIndex

-0.30

 Horseshoe

-0.30

 ThemeData

-0.29

horloge

-0.29

 Matériau

-0.28

 corrida

-0.28

 Highland

-0.28

 Secretaría

-0.28

Histoire

-0.28

 graphique

-0.28

POSITIVE LOGITS

SharedDtor

0.63

0.58

 AttributeSet

0.57

󠁢

0.56

出版年

0.56

Искәрмәләр

0.54

lator

0.54

ardized

0.54

TypedDataSet

0.54

 فريبيس

0.54

Activations Density 1.371%

terms related to formal approvals and actions

No Comments

No Known Activations