INDEX

Explanations

assignment operations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 ustedes

-0.61

CommonModule

-0.58

’

-0.58

ers

-0.57

kirch

-0.56

Hoy

-0.56

foro

-0.56

儀

-0.56

ous

-0.55

Bub

-0.55

POSITIVE LOGITS

/=

1.82

>=</

1.50

1.44

}=

1.28

.=

1.28

_=

1.26

$=\

1.24

)=

1.23

}}=$

1.22

$=

1.20

Activations Density 0.371%

assignment operations in code

No Comments

No Known Activations