INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

}\]

-0.84

})

-0.82

"):

-0.81

 }}$}

-0.81

 itſelf

-0.78

 pleaſure

-0.78

})}

-0.78

 Diſ

-0.77

")]

-0.77

POSITIVE LOGITS

 love

1.11

 loves

0.87

 loved

0.87

love

0.81

 Love

0.78

 LOVE

0.75

 loving

0.73

 affection

0.73

Love

0.70

Loves

0.65

Activations Density 0.046%

No Comments

No Known Activations