INDEX

Explanations

assertion statements used in testing code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Poincar

-0.60

multer

-0.59

 relâche

-0.55

 dataSnapshot

-0.53

 veneer

-0.53

 Euphrates

-0.53

 οποίο

-0.51

бенок

-0.50

 fVar

-0.50

fly

-0.49

POSITIVE LOGITS

assertEquals

1.31

assertEqual

1.00

AreEqual

0.98

toEqual

0.89

 مرئيه

0.86

 continúas

0.73

 disambiguazione

0.72

BrowserModule

0.71

$}}

0.70

GOTREF

0.67

Activations Density 0.048%

assertion statements used in testing code

No Comments

No Known Activations