INDEX

Explanations

references to widgets and their properties in code

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

contentLoaded

-0.97

Aiheesta

-0.79

 fotografico

-0.78

#![

-0.78

createCanvas

-0.75

 useStyles

-0.74

 abbigliamento

-0.73

 UnityEngine

-0.72

SuppressMessage

-0.71

 RouterModule

-0.71

POSITIVE LOGITS

 widget

2.01

 Widget

1.89

 widgets

1.85

 Widgets

1.81

widget

1.77

 createState

1.70

Widget

1.70

widgets

1.53

Widgets

1.51

WIDGET

1.36

Activations Density 0.141%

references to widgets and their properties in code

No Comments

No Known Activations