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

DrawerLayout

-0.73

mybatisplus

-0.72

(__('

-0.64

RegisterType

-0.62

AccessFile

-0.61

}{*}{

-0.59

TypeDef

-0.59

YOND

-0.57

 Gorb

-0.56

RemoteException

-0.56

POSITIVE LOGITS

stimulus

2.63

 stimulus

1.98

 Stimulus

1.84

 stimuli

1.51

 jsPsych

1.48

Stim

1.34

stim

1.19

 Stim

1.11

 estí

1.02

 estímulo

0.99

Activations Density 0.002%

No Comments

No Known Activations