INDEX

Explanations

mathematical symbols and notation related to higher dimensions and algebraic expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 saites

-1.04

 propOrder

-1.02

 Jaros

-0.96

 Jarvis

-0.96

 noDo

-0.92

 doubtnut

-0.90

Yad

-0.90

 Selva

-0.89

 linkovi

-0.88

ISD

-0.87

POSITIVE LOGITS

^{\

2.29

 }^{\

2.04

}^{\

2.00

)^{\

1.98

}}^{\

1.62

]^{\

1.58

^{\

1.54

 }}^{\

1.43

^\

1.25

$^{\

1.20

Activations Density 0.118%

mathematical symbols and notation related to higher dimensions and algebraic expressions

No Comments

No Known Activations