INDEX

Explanations

words and phrases associated with "wh" sounds, indicating a focus on interrogative expressions or inquiries

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

 Abia

-0.62

edonia

-0.50

utah

-0.49

ransition

-0.48

weaver

-0.48

profen

-0.47

 Arlene

-0.47

 Crusoe

-0.47

ekt

-0.47

 Helena

-0.47

POSITIVE LOGITS

Wh

1.48

Wh

1.48

wh

1.44

wh

1.38

WH

1.38

WH

1.23

 WHIT

1.02

 Whit

0.99

Whi

0.95

Whit

0.94

Activations Density 0.201%

words and phrases associated with "wh" sounds, indicating a focus on interrogative expressions or inquiries

No Comments

No Known Activations