INDEX

Explanations

significant elements related to key events and figures in news articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

CppMethod

-0.94

 فريبيس

-0.85

 propOrder

-0.84

SourceChecksum

-0.83

Jîn

-0.78

webElementXpaths

-0.77



-0.73

 يتيمه

-0.73

RefNanny

-0.71

 autorytatywna

-0.69

POSITIVE LOGITS

 upside

0.28

@@@@@

0.27

</em>

0.27

bit

0.26

sat

0.25

 stop

0.25

me

0.24

wh

0.24

sy

0.24

 Scha

0.24

Activations Density 0.837%

significant elements related to key events and figures in news articles

No Comments

No Known Activations