INDEX

Explanations

references to historical events, particularly wars and inventions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

tvrt

-0.57

 McKnight

-0.57

unnitel

-0.55

ptonshire

-0.54

貼

-0.50

nappropriate

-0.49

 Mitar

-0.48

jog

-0.48

Etape

-0.47

راتيج

-0.47

POSITIVE LOGITS

WWI

0.69

mybatisplus

0.68

expandindo

0.65

endphp

0.65

ţei

0.63

gatsby

0.60

 Bolshe

0.60

 propOrder

0.59

 itſelf

0.58

ectoria

0.58

Activations Density 0.906%

references to historical events, particularly wars and inventions

No Comments

No Known Activations