INDEX

Explanations

various numeric values and identifiers related to data structures or programming constructs

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

Numbers followed by a digit or letter

np_acts-logits-general · gemini-2.0-flash

UUIDs and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ftagPool

-0.58

 ModelExpression

-0.45

MLLoader

-0.42

 الحره

-0.40

AndEndTag

-0.40

fjspx

-0.39

/**

-0.39

featureID

-0.39

migrationBuilder

-0.39

IsContent

-0.39

POSITIVE LOGITS

Personendaten

0.63

 discorso

0.44

 slutt

0.43

 sää

0.43

יסטור

0.43

anmoins

0.43

 Grecs

0.42

 Stringer

0.42

 specchio

0.42

TION

0.42

Activations Density 0.342%

various numeric values and identifiers related to data structures or programming constructs

Numbers followed by a digit or letter

UUIDs and identifiers

No Comments

No Known Activations