INDEX

Explanations

positive descriptors and characteristics related to individuals

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

Followed by a noun referring to people

np_acts-logits-general · gemini-2.0-flash

positive descriptions of people

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

 Приступљено

-0.65

)();

-0.62

 Administrativna

-0.61

coroutines

-0.57

ViewFeatures

-0.56

MemoryWarning

-0.55

izarse

-0.54

poň

-0.53

Jeografia

-0.53

migrationBuilder

-0.52

POSITIVE LOGITS

 person

1.50

 Person

1.11

 PERSON

1.06

person

1.06

 pessoa

1.05

 persons

1.02

Person

0.99

PERSON

0.93

 persoon

0.92

 human

0.90

Activations Density 0.176%

positive descriptors and characteristics related to individuals

Followed by a noun referring to people

positive descriptions of people

No Comments

No Known Activations