INDEX

Explanations

numerical data and statistical representations

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

or

-0.63

-0.52

 most

-0.52

Most

-0.50

—

-0.46

—

-0.46

 Most

-0.45

 design

-0.45

-0.44

↵↵

-0.43

POSITIVE LOGITS

PreferredItem

1.13

IntoConstraints

1.11

 насељу

1.10

 Exacts

0.99

(;;)

0.95

MemoryWarning

0.94

 betweenstory

0.94

^(@)

0.92

FunctionFlags

0.91

 createState

0.90

Activations Density 0.152%

numerical data and statistical representations

No Comments

No Known Activations