INDEX

Explanations

references to historical events and notable figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ThroughAttribute

-0.61

 MANY

-0.57

 <<<<<<<<<<<<<<

-0.56

elson

-0.55

 ويكيميديا

-0.54

ługo

-0.52

 المعيارى

-0.52

 many

-0.51

󠁢

-0.51

蚪

-0.50

POSITIVE LOGITS

 defaultstate

0.62

 részt

0.59

niosek

0.54

RegistryLite

0.54

DockStyle

0.53

 palk

0.52

 صوتيه

0.52

])/

0.52

MemoryWarning

0.51

CompilerServices

0.51

Activations Density 0.088%

references to historical events and notable figures

No Comments

No Known Activations