INDEX

Explanations

references to specific locations and communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 AssemblyCulture

-0.65

FXMLLoader

-0.62

stdc

-0.62

Abitanti

-0.58

vestream

-0.58

 Orrell

-0.57

runApp

-0.56

 وتسجيلات

-0.56

endenza

-0.55

ecap

-0.55

POSITIVE LOGITS

 EconPapers

0.56

 resourceCulture

0.55

 tartalomajánló

0.50

 purpoſe

0.49

 مفص

0.49

Referències

0.47

 okuyayım

0.47

richTextPanel

0.47

页面存档备份

0.46

Erreferentziak

0.46

Activations Density 0.591%

references to specific locations and communities

No Comments

No Known Activations