INDEX

Explanations

numerical data related to measurements and values

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

RenderAtEndOf

-0.88

RTEE

-0.80

存于互联网档案馆

-0.80

Efq

-0.79

rungsseite

-0.79

();)

-0.74

`,

-0.72

 itſelf

-0.71

 myſelf

-0.71

الحياه

-0.69

POSITIVE LOGITS

AppCompatTheme

0.43

↵↵

0.42

<eos>

0.41

 Cicero

0.40

buried

0.40

LIC

0.39

currentColor

0.39

IsContent

0.39

prefixer

0.38

WebVitals

0.38

Activations Density 0.182%

numerical data related to measurements and values

No Comments

No Known Activations