INDEX

Explanations

mathematical symbols and notation related to functions and transformations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 propOrder

-1.01

 saites

-0.97

IUrlHelper

-0.92

MTL

-0.91

Yad

-0.89

 Maitland

-0.89

 Saif

-0.87

asList

-0.84

 jadx

-0.83

 Selva

-0.81

POSITIVE LOGITS

^{\

1.52

)^{\

1.43

 }^{\

1.40

}^{\

1.29

}}^{\

1.00

]^{\

0.99

 }}^{\

0.97

^{\

0.93

 $^{\

0.93

′

0.75

Activations Density 0.229%

mathematical symbols and notation related to functions and transformations

No Comments

No Known Activations