INDEX

Explanations

names of historical figures and significant entities related to various events or topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

WaitGroup

-0.27

 strutture

-0.27

nargs

-0.25

 escalera

-0.25

 migrantes

-0.24

fix

-0.23

fhir

-0.23

 great

-0.22

 favor

-0.22

POSITIVE LOGITS

 indisponible

0.67

//});

0.67

 }}$}

0.64

%)$

0.63

 zuſammen

0.63

存档备份

0.63

 surla

0.63

httphttps

0.62

$_=

0.62

 onCreateView

0.61

Activations Density 2.205%

names of historical figures and significant entities related to various events or topics

No Comments

No Known Activations