INDEX

Explanations

references to death or burial events

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

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

Handlung

-0.56

antMatchers

-0.55

verwijspagina

-0.55

opress

-0.53

tocin

-0.52

 emend

-0.51

ElementAt

-0.50

 éto

-0.50

الحياه

-0.49

topLeft

-0.49

POSITIVE LOGITS

 funeral

2.11

 burial

1.81

 Funeral

1.81

Funeral

1.66

 funerals

1.63

funeral

1.63

 mourners

1.60

 Burial

1.60

 cremation

1.59

 coffin

1.54

Activations Density 0.284%

references to death or burial events

No Comments

No Known Activations