INDEX

Explanations

technical terms related to data analysis or programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

EndInit

-0.68

 MainAxisSize

-0.68

StoryboardSegue

-0.67

BeginInit

-0.64

Datuak

-0.63

 مشين

-0.60

AddTagHelper

-0.59

 تكبرها

-0.58

 defaultstate

-0.58

 للمعارف

-0.56

POSITIVE LOGITS

0.99

0.94

0.93

FF

0.87

 fluoride

0.85

FF

0.84

 Francis

0.83

ff

0.81

fi

0.81

Activations Density 2.025%

technical terms related to data analysis or programming

No Comments

No Known Activations