INDEX

Explanations

references to closeness or proximity in various contexts

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

 propOrder

-0.83

AutoScale

-0.79

 OnTriggerEnter

-0.74

)))));

-0.74

 الاطلاع

-0.72

 ویکی‌پدیای

-0.70

 inappropriés

-0.67

DIPSETTING

-0.66

Abitanti

-0.65

 useParams

-0.64

POSITIVE LOGITS

 close

1.13

close

0.90

 Close

0.81

Close

0.77

 CLOSE

0.70

 coffee

0.65

Fecha

0.55

CLOSE

0.52

 counter

0.52

closeButton

0.50

Activations Density 0.104%

references to closeness or proximity in various contexts

No Comments

No Known Activations