INDEX

Explanations

phrases related to public perceptions and portrayals of individuals in various contexts

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

followed by prepositions or pronouns

np_acts-logits-general · gemini-2.0-flash

said that, report before, bounty for, reason for, warrant for

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

istoitu

-0.42

UnknownFieldSet

-0.42

ειτουργ

-0.42

횟

-0.40

 خود

-0.40

providedIn

-0.38

">//

-0.38

ingeki

-0.37

evos

-0.37

 Lokales

-0.37

POSITIVE LOGITS

把他

0.81

ihn

0.80

him

0.79

将他

0.79

 그의

0.76

這位

0.69

 biographical

0.69

his

0.68

这位

0.67

 honom

0.66

Activations Density 0.709%

phrases related to public perceptions and portrayals of individuals in various contexts

followed by prepositions or pronouns

said that, report before, bounty for, reason for, warrant for

No Comments

No Known Activations