INDEX

Explanations

references to political events and figures

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

Personendaten

-0.42

mē

-0.36

 uska

-0.35

Parcelize

-0.35

 potr

-0.34

my

-0.33

 touch

-0.33

'])){

-0.33

 fleet

-0.32

}))

-0.30

POSITIVE LOGITS

 EconPapers

0.70

contentLoaded

0.69

 <<<<<<<<<<<<<<

0.65

 fubject

0.56

 invokingState

0.54

 لينك

0.53

 &___

0.53

❋

0.53

 himſelf

0.52

ThroughAttribute

0.52

Activations Density 1.928%

references to political events and figures

No Comments

No Known Activations