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

 myſelf

-1.01

 himſelf

-0.96

 cauſe

-0.96

 fubject

-0.94

 uſed

-0.93

 raiſ

-0.93

 purpoſe

-0.90

 ſtand

-0.89

 ſtate

-0.89

 ſche

-0.88

POSITIVE LOGITS

 like

0.88

0.84

 akin

0.79

 Like

0.75

an

0.73

like

0.71

就像是

0.70

Like

0.66

まるで

0.65

 resembles

0.65

Activations Density 0.080%

No Comments

No Known Activations