INDEX

Explanations

contextual information related to technology and user interaction with devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

tagHelperRunner

-0.74

Gön

-0.67

Aiheesta

-0.63

glMatrixMode

-0.57

MethodManager

-0.56

 مرئيه

-0.56

apal

-0.55

 AssemblyCulture

-0.52

IUrlHelper

-0.52

 Wikimedijinoj

-0.50

POSITIVE LOGITS

 الفلك

0.58

 unknownFields

0.57

ago

0.55

 obstante

0.53

stuhl

0.52

initComponents

0.50

 quenched

0.50

Bissau

0.49

TEMPERATURE

0.49

 RemoteException

0.48

Activations Density 0.214%

contextual information related to technology and user interaction with devices

No Comments

No Known Activations