INDEX

Explanations

phrases indicating expertise and experience in various fields

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

expertise/knowledge

np_acts-logits-general · gemini-2.0-flash

unique knowledge and expertise

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

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

########.

-0.57

AndEndTag

-0.50

IContainer

-0.50

 kasarigan

-0.49

音を

-0.48

 encarga

-0.46

ViewImports

-0.46

Obrázky

-0.46

 pari

-0.45

ero

-0.45

POSITIVE LOGITS

 expertise

1.36

expertise

1.22

 Expertise

1.16

Expertise

1.15

 knowledge

1.07

 knowled

0.97

 expert

0.95

 EXPERT

0.93

 experto

0.92

knowledge

0.90

Activations Density 0.251%

phrases indicating expertise and experience in various fields

expertise/knowledge

unique knowledge and expertise

No Comments

No Known Activations