INDEX

Explanations

technical terms related to graphical or layout positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

ekte

-0.47

“

-0.46

 developments

-0.45

Resources

-0.44

 Resources

-0.44

 resources

-0.43

 grand

-0.43

 post

-0.43

-0.42

POSITIVE LOGITS

MigrationBuilder

1.13

 ExecuteAsync

1.10

 myſelf

0.90

 purpoſe

0.86

UnusedPrivate

0.86

 Monfieur

0.85

 оригіналу

0.84

Gambas

0.83

 للاسماء

0.83

 uſed

0.81

Activations Density 0.023%

technical terms related to graphical or layout positioning

No Comments

No Known Activations