INDEX

Explanations

mentions of shops and shopping-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

complexContent

-0.81

存于互联网档案馆

-0.75

styleType

-0.75

 tartalomajánló

-0.74

ConstraintMaker

-0.74

NameInMap

-0.73

 disambiguazione

-0.72

 <=",

-0.70

 Normdatei

-0.69

 Infórmanos

-0.69

POSITIVE LOGITS

 shops

0.75

Shops

0.74

 Shops

0.72

shops

0.69

 SHOP

0.62

 shop

0.61

bop

0.59

keepers

0.56

SHOP

0.56

hops

0.53

Activations Density 0.050%

mentions of shops and shopping-related terms

No Comments

No Known Activations