INDEX

Explanations

numerical values and related statistical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

aarrggbb

-0.88

AsUp

-0.80

AndEndTag

-0.80

 Италијани

-0.78

kháu

-0.76

EDEFAULT

-0.76

Hochspringen

-0.70

TypedDataSet

-0.67

Citiți

-0.67

 jspb

-0.66

POSITIVE LOGITS

SupportActionBar

0.58

RUnlock

0.50

0.48

 ویکی‌پدیا

0.48

存于互联网档案馆

0.47

ратор

0.46

 bronzo

0.46

autoconfigure

0.46

 Dafür

0.44

endregion

0.44

Activations Density 0.145%

numerical values and related statistical terms

No Comments

No Known Activations