INDEX

Explanations

phrases indicating causation or reasons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Mô

-0.64

 myſelf

-0.57

 himſelf

-0.55

 Athenians

-0.55

WebControls

-0.53

 ་་

-0.52

 itſelf

-0.51

toMatchSnapshot

-0.51

SharedDtor

-0.50

 Weyl

-0.49

POSITIVE LOGITS

 lack

1.16

 adanya

0.90

 reasons

0.88

lack

0.86

its

0.85

 necessity

0.83

 nature

0.78

 being

0.78

 their

0.75

 limitations

0.74

Activations Density 0.234%

phrases indicating causation or reasons

No Comments

No Known Activations