INDEX

Explanations

phrases related to complex or multiple group identities and classifications

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

quantities of two or more

np_acts-logits-general · gemini-2.0-flash

multiple

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

MigrationBuilder

-0.48

jsonwebtoken

-0.42

 feltro

-0.41

contentLoaded

-0.40

 Италијани

-0.39

toplankton

-0.39

UnsafeEnabled

-0.39

Jîn

-0.39

Jeografia

-0.38

новништво

-0.38

POSITIVE LOGITS

 multiple

2.28

multiple

2.03

Multiple

1.90

 Multiple

1.87

 MULTIPLE

1.80

 meerdere

1.69

MULTIPLE

1.65

複数の

1.63

複数

1.59

 mehrere

1.51

Activations Density 1.070%

phrases related to complex or multiple group identities and classifications

quantities of two or more

multiple

No Comments

No Known Activations