INDEX

Explanations

numerical data and statistics related to observations or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

homonymie

-0.56

FunctionFlags

-0.51

 intStringLen

-0.50

냥

-0.49

ंदीखरीदारी

-0.46

 ujednoznacz

-0.45

 allan

-0.44

 vieilles

-0.44

 gammel

-0.43

 CreateTagHelper

-0.42

POSITIVE LOGITS

ArgsConstructor

0.65

 ویکی‌پدی

0.65

 Савез

0.62

出版年

0.60

 Richelieu

0.53

 ImportError

0.53

argout

0.52

contentLoaded

0.52

FieldBuilder

0.52

Semi

0.51

Activations Density 0.584%

numerical data and statistics related to observations or results

No Comments

No Known Activations