INDEX

Explanations

phrases indicating varying degrees of quantity or extent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Obrázky

-0.73

########.

-0.71

 تانيه

-0.70

 snippetHide

-0.67

 justiça

-0.67

 actuelles

-0.65

 labors

-0.62

 gevolg

-0.61

htë

-0.60

 Wikimedijinoj

-0.60

POSITIVE LOGITS

なるべく

0.60

 autant

0.59

 ComVisible

0.56

 every

0.55

0.52

jot

0.51

DrawerToggle

0.51

JsonProperty

0.50

できるだけ

0.49

 either

0.49

Activations Density 0.131%

phrases indicating varying degrees of quantity or extent

No Comments

No Known Activations