INDEX

Explanations

proper nouns, particularly names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AndEndTag

-0.63

✨:

-0.62

qrstuvwxyz

-0.55

 Hauptstadt

-0.53

 textStatus

-0.53

umenter

-0.52

IntoConstraints

-0.48

abello

-0.48

mær

-0.47

 république

-0.47

POSITIVE LOGITS

SourceChecksum

0.67

 invokingState

0.62

__*/

0.50

AntiForgeryToken

0.50

 iParam

0.49

archiviato

0.49

teve

0.49

UnusedPrivate

0.49

0.48

 đón

0.48

Activations Density 0.213%

proper nouns, particularly names

No Comments

No Known Activations