INDEX

Explanations

programming-related terms and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

-0.41

heavy

-0.40

ross

-0.40

 donc

-0.39

 heavy

-0.38

cow

-0.38

 '*',

-0.37

اسف

-0.37

 électriques

-0.36

POSITIVE LOGITS

 transférez

0.87

NUMX

0.86

 propOrder

0.77

Билгалдахарш

0.74

 חיצוניים

0.73

NameInMap

0.71

 initComponents

0.70

Lähteet

0.70

 BoxDecoration

0.68

 MaterialApp

0.67

Activations Density 0.249%

programming-related terms and structures

No Comments

No Known Activations