INDEX

Explanations

mathematical symbols and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

endphp

-0.75

Gweler

-0.66

 forState

-0.60

copg

-0.60

:✨

-0.59

NSYLVANIA

-0.56

/**

-0.56

mstyle

-0.55

expandindo

-0.54

-0.53

POSITIVE LOGITS

 BorderRadius

0.55

 Monfieur

0.55

\{\\

0.54

 ་་

0.50

 itſelf

0.49

 ―――――

0.49

Nguyên

0.48

 doubtnut

0.47

acyjna

0.47

heber

0.47

Activations Density 0.035%

mathematical symbols and notations

No Comments

No Known Activations