INDEX

Explanations

references to stickers and sticker-related content

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

stickers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

QMetaType

-0.54

-0.50

BCE

-0.48

 "..\..\..\

-0.48

 للمعارف

-0.47

─

-0.47

),

-0.47

\)

-0.46

tableFuture

-0.46

POSITIVE LOGITS

 sticker

2.03

 stickers

1.95

 Sticker

1.85

Sticker

1.76

 Stickers

1.72

sticker

1.65

stickers

1.50

 pegatinas

1.31

 pegatina

1.27

 stiker

1.21

Activations Density 0.001%

references to stickers and sticker-related content

stickers

No Comments

No Known Activations

references to stickers and sticker-related content

stickers

No Comments

No Known Activations