INDEX

Explanations

comments and annotations in code

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

Code comments with @author, @fileoverview, or @package

np_acts-logits-general · gemini-2.0-flash

author tags

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FailureListener

-0.97

تقاوى

-0.84

ChildScrollView

-0.76

DockStyle

-0.75

endphp

-0.74

 ويكيپيديا

-0.72

featureID

-0.70

AnchorStyles

-0.70

<?

-0.69

 demografica

-0.69

POSITIVE LOGITS

↵

0.62

↵↵

0.54

Author

0.51

<h2>

0.49

تم

0.48

<blockquote>

0.46

0.45

 quill

0.45

 senhor

0.45

author

0.45

Activations Density 0.016%

comments and annotations in code

Code comments with @author, @fileoverview, or @package

author tags

No Comments

No Known Activations