INDEX

Explanations

terms related to secondary and tertiary classifications or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ånga

-0.49

ppone

-0.49

uronic

-0.46

getLong

-0.46

 popular

-0.45

multer

-0.44

AttributeValue

-0.44

ComponentScan

-0.44

putan

-0.44

шкан

-0.43

POSITIVE LOGITS

 secondary

1.35

 Secondary

1.31

Secondary

1.27

secondary

1.19

 SECONDARY

1.17

 sekund

1.12

 Primary

1.07

SECONDARY

1.07

PRIMARY

1.03

 PRIMARY

1.03

Activations Density 0.998%

terms related to secondary and tertiary classifications or conditions

No Comments

No Known Activations