INDEX

Explanations

repeated mentions of the word "you."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 settore

-0.43

 oeil

-0.42

 affari

-0.40

ostante

-0.39

<h2>

-0.39

 McFadden

-0.39

pośred

-0.38

 antichi

-0.37

 bénévol

-0.37

 Schmid

-0.36

POSITIVE LOGITS

you

1.16

You

1.11

YOU

1.05

YOU

1.00

you

0.96

You

0.92

your

0.88

uxxxx

0.87

rungsseite

0.85

yourself

0.85

Activations Density 0.173%

repeated mentions of the word "you."

No Comments

No Known Activations