INDEX

Explanations

bullet points and key highlights in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ILayout

-0.59

قایناق‌لار

-0.52

henswürdigkeiten

-0.51

orance

-0.51

ooplankton

-0.50

理石

-0.50

 Tans

-0.50

徨

-0.49

⦒

-0.49

 zeitung

-0.49

POSITIVE LOGITS

•

1.56

••

1.34

•••

1.29

•

1.27

.•

1.25

••••

1.23

)•

1.16

 ••

1.11

~•

1.05

€¢

0.90

Activations Density 0.170%

bullet points and key highlights in a document

No Comments

No Known Activations