INDEX

Explanations

references to borrowing, copying, or inheriting ideas and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

:✨

-0.72

 beginnetje

-0.69

bitat

-0.66

WriteBarrier

-0.62

 myſelf

-0.62

/***/

-0.62

UIControlState

-0.61

afficheront

-0.61

 auxquelles

-0.60

bolista

-0.60

POSITIVE LOGITS

 borrowed

1.07

 borrow

1.00

 borrowing

0.99

 Borrow

0.84

borrow

0.83

 BORROW

0.82

Borrow

0.79

Copy

0.77

 Copy

0.77

 copied

0.77

Activations Density 0.683%

references to borrowing, copying, or inheriting ideas and concepts

No Comments

No Known Activations