INDEX

Explanations

mentions of brands and product specifications

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

Follows brand names

np_acts-logits-general · gemini-2.0-flash

company brands and designer names

np_acts-logits-general · gemini-2.5-flash-lite

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

Билгалдахарш

-0.75

RenderAtEndOf

-0.65

awtextra

-0.62

 calendriers

-0.59

 nakalista

-0.55

VIAF

-0.53

 secondaires

-0.52

ChildScrollView

-0.52

unhofer

-0.52

ztes

-0.50

POSITIVE LOGITS

 brand

2.37

 brands

2.36

brand

2.15

brands

2.00

 Brand

1.98

Brand

1.97

 branded

1.91

 BRAND

1.91

 Brands

1.88

BRAND

1.80

Activations Density 0.108%

mentions of brands and product specifications

Follows brand names

company brands and designer names

No Comments

No Known Activations