INDEX

Explanations

expressions of curiosity or doubt

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

followed by questions

np_acts-logits-general · gemini-2.0-flash

expressing wonder or curiosity

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

AntiForgeryToken

-0.66

ifié

-0.60

bigliamento

-0.57

 Astoria

-0.57

bebasan

-0.56

 Vass

-0.56

aronne

-0.55

🔥🔥

-0.54

oinette

-0.53

 отношению

-0.53

POSITIVE LOGITS

 wonder

1.06

 wondering

1.02

wonder

1.02

 WONDER

0.93

 wondered

0.93

 Wonder

0.91

 doubt

0.87

Wondering

0.86

Wonder

0.86

why

0.78

Activations Density 0.067%

expressions of curiosity or doubt

followed by questions

expressing wonder or curiosity

No Comments

No Known Activations