INDEX

Explanations

hyperlinks and references to additional resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

 CreateTagHelper

-0.83

ⓧ

-0.71

ImageContext

-0.70

AndEndTag

-0.68

UnusedPrivate

-0.67

 Baillargeon

-0.67

 <=",

-0.66

LookAnd

-0.65

IntoConstraints

-0.63

 propOrder

-0.62

POSITIVE LOGITS

ihnachten

0.54

ariate

0.53

Latch

0.52

åg

0.52

żeli

0.46

 Garnish

0.45

ArgsConstructor

0.45

redited

0.45

ioms

0.45

”、“

0.45

Activations Density 0.017%

hyperlinks and references to additional resources

No Comments

No Known Activations