INDEX

Explanations

phrases discussing interventions and their impact on various social or health-related issues

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

Follows a noun/topic with an associated activity/sequence

np_acts-logits-general · gemini-2.0-flash

United States, any, by, oleh

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 GenerationType

-0.61



-0.60

StoryboardSegue

-0.59

parsedMessage

-0.58

 Biôgrafia

-0.57

DockStyle

-0.56

orianCalendar

-0.56

出版年

-0.55

RectangleBorder

-0.55

HostException

-0.54

POSITIVE LOGITS

 oneself

0.47

 anyone

0.43

Anyone

0.42

 bagi

0.42

 Anyone

0.41

by

0.39

 members

0.39

anyone

0.38

 ANYONE

0.36

 oleh

0.34

Activations Density 0.725%

phrases discussing interventions and their impact on various social or health-related issues

Follows a noun/topic with an associated activity/sequence

United States, any, by, oleh

No Comments

No Known Activations