INDEX

Explanations

mathematical notations related to operators and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

-1.02

 saites

-0.97

IUrlHelper

-0.97

 Maitland

-0.88

Yad

-0.88

 Saif

-0.86

MTL

-0.86

 Grau

-0.86

 Dynamo

-0.84

 houses

-0.84

POSITIVE LOGITS

^{\

1.58

 }^{\

1.52

)^{\

1.46

}^{\

1.32

^{\

1.14

}}^{\

1.08

]^{\

1.03

 }}^{\

0.97

 $^{\

0.90

{{\

0.87

Activations Density 0.145%

mathematical notations related to operators and their properties

No Comments

No Known Activations