INDEX

Explanations

values associated with significant measurements or results

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

Code or special characters

np_acts-logits-general · gemini-2.0-flash

Objective-C selectors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

ChildScrollView

-0.66

OGND

-0.58

@[+][

-0.58

MigrationBuilder

-0.57

 sukienka

-0.56

 Numerade

-0.56

ArrowToggle

-0.56

oredCriteria

-0.54

PreferredItem

-0.53

 Bioaccumulative

-0.53

POSITIVE LOGITS

 McCar

0.36

 HasFactory

0.35

engk

0.33

landt

0.32

 برانيه

0.32

*/}

0.32

?>/

0.31

/'.$

0.31

elt

0.31

ha

0.30

Activations Density 0.117%

values associated with significant measurements or results

Code or special characters

Objective-C selectors

No Comments

No Known Activations