INDEX

Explanations

references to vertical orientation or positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

URLException

-0.77

 ſhall

-0.72

󠁢

-0.71

//

-0.70

EndInit

-0.69

GEBURTSDATUM

-0.67

'},

-0.64

ksesta

-0.64

AnimationsModule

-0.62

fulness

-0.62

POSITIVE LOGITS

他

0.70

jej

0.58

 його

0.58

 horiz

0.57

我

0.57

 horizontal

0.57

 её

0.57

TintMode

0.55

 vertical

0.55

她

0.54

Activations Density 0.056%

references to vertical orientation or positioning

No Comments

No Known Activations