INDEX

Explanations

terms related to computer programming or software development, particularly involving "com" prefix variables

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

The token "com" and variations

np_acts-logits-general · gemini-2.0-flash

com prefix

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

expandindo

-0.85

bootstrapcdn

-0.84

GEBURTSDATUM

-0.80

EndInit

-0.80

 متعلقه

-0.79

 propOrder

-0.78

 tartalomajánló

-0.77

\{\\

-0.77

Hauptartikel

-0.76

///</

-0.75

POSITIVE LOGITS

COM

1.00

COM

0.98

Com

0.98

 COMM

0.89

Com

0.87

Kom

0.87

KOM

0.83

kom

0.79

Kom

0.78

com

0.76

Activations Density 0.521%

terms related to computer programming or software development, particularly involving "com" prefix variables

The token "com" and variations

com prefix

No Comments

No Known Activations