INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nakalista

-0.58

 CreateTagHelper

-0.57

########.

-0.57

ohistochemistry

-0.52

)_/¯

-0.48

 resourceCulture

-0.47

例文帳に追加

-0.47

HideInInspector

-0.47

waitKey

-0.46

anskje

-0.46

POSITIVE LOGITS

interopRequire

0.73

AnchorStyles

0.70

Архівовано

0.67

 BorderRadius

0.63

ագրություններ

0.60

 ***!

0.59

 getattr

0.58

IntoConstraints

0.58

MessageState

0.57

kozások

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.