INDEX

Explanations

references to mathematical symbols and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

and

-0.62

me

-0.58

is

-0.57

ALL

-0.57

 kids

-0.56

 FREE

-0.56

ar

-0.55

one

-0.55

 waters

-0.55

 Gerr

-0.55

POSITIVE LOGITS

setVerticalGroup

1.21

 insuffisamment

0.99

 AssemblyCulture

0.93

findpost

0.92

didSet

0.89

".

0.88

])));

0.85

 familières

0.82

")));

0.82

})).

0.81

Activations Density 1.448%

references to mathematical symbols and notation

No Comments

No Known Activations