INDEX

Explanations

formatting elements typically used in mathematical expressions or equations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

DoubleQuotes

-0.74

__.__

-0.66

 استنادى

-0.63

ViewFeatures

-0.63

 invokingState

-0.61

FetchType

-0.61

">$

-0.61

})->

-0.60

 Tind

-0.59

alamy

-0.58

POSITIVE LOGITS

bibitem

0.79

0.70

 متعلقه

0.68

GEBURTSDATUM

0.67

NameInMap

0.65

itsub

0.64

subsubsection

0.59

TagMode

0.58

 AssemblyTitle

0.56

StoreMessageInfo

0.55

Activations Density 0.330%

formatting elements typically used in mathematical expressions or equations

No Comments

No Known Activations