INDEX

Explanations

phrases related to urgent actions and recommendations

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

urgency or immediacy

np_acts-logits-general · gemini-2.0-flash

immediate action required

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

Occasionally

-0.58

 Occasionally

-0.57

 ujednoznacz

-0.57

aughey

-0.56

 successive

-0.55

fitri

-0.54

[]=$

-0.53

miny

-0.53

extField

-0.50

ChildIndex

-0.50

POSITIVE LOGITS

now

2.40

NOW

2.21

now

2.06

NOW

1.98

 immediately

1.93

Now

1.88

 today

1.85

Now

1.81

immediately

1.76

 sekarang

1.75

Activations Density 0.305%

phrases related to urgent actions and recommendations

urgency or immediacy

immediate action required

No Comments

No Known Activations