INDEX

Explanations

mathematical symbols and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

LookAnd

-0.68

 okuyayım

-0.53

 propOrder

-0.52

Datuak

-0.51

 Meksiku

-0.47

hoeddwyd

-0.47

guém

-0.47

 ویکی‌پدی

-0.45

 wiedzy

-0.45

 desplaz

-0.44

POSITIVE LOGITS

<th>

0.95

 Twitter

0.50

{\

0.48

FieldNumber

0.44

人物

0.42

Twitter

0.41

儡

0.41

 mors

0.40

BRON

0.39

ReferenceEquals

0.39

Activations Density 0.159%

mathematical symbols and notations

No Comments

No Known Activations

mathematical symbols and notations

No Comments

No Known Activations