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

ConstraintMaker

-0.88

StoryboardSegue

-0.81

+#+#

-0.79

IsMutable

-0.77

Према

-0.77

AddTagHelper

-0.74

 للمعارف

-0.73

ScopeManager

-0.68

RectangleBorder

-0.66

insics

-0.66

POSITIVE LOGITS

readlines

0.53

readLine

0.52

一行

0.50

itada

0.47

nextLine

0.47

lines

0.46

 line

0.46

multiline

0.45

 lines

0.45

readline

0.44

Activations Density 0.039%

No Comments

No Known Activations