INDEX

Explanations

references to numerical values or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 '/';

-0.87

]+=

-0.80

\}\\

-0.78

колеп

-0.76

">:

-0.75

})}

-0.74

()<<

-0.74

::::::::::::::::

-0.74

EDR

-0.73

EDR

-0.72

POSITIVE LOGITS

Num

1.34

num

1.34

num

1.31

Num

1.22

 nums

1.18

setNum

1.14

NUM

1.09

getNum

1.07

nums

1.06

numRows

1.03

Activations Density 0.073%

references to numerical values or quantities

No Comments

No Known Activations