INDEX

Explanations

phrases that indicate questions or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ſelf

-0.56

izoen

-0.55

 fufficient

-0.52

Efq

-0.52

Czytaj

-0.51

gyz

-0.49

териалы

-0.49

 Tiểu

-0.48

YSTEM

-0.48

beiter

-0.48

POSITIVE LOGITS

ISupport

0.86

richTextPanel

0.86

IsContent

0.76

}),

0.68

ंदीखरीदारी

0.67

writeField

0.66

!*\

0.65

”)

0.64

InjectAttribute

0.63

 насељу

0.62

Activations Density 0.131%

phrases that indicate questions or uncertainty

No Comments

No Known Activations