INDEX

Explanations

phrases indicating communication or interaction requests

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

Follows punctuation in various contexts

np_acts-logits-general · gemini-2.0-flash

prediction: Aston Villa

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

hya

-0.41

sterdam

-0.41

هران

-0.40

thodes

-0.40

 here

-0.39

he

-0.38

PropertyChanging

-0.38

go

-0.38

ctice

-0.38

 quedado

-0.37

POSITIVE LOGITS

 فريبيس

0.76

 Signalez

0.72

 Humb

0.72

ViewFeatures

0.72

utnik

0.71

contentLoaded

0.71

MENAFN

0.70

 NUKAT

0.69

parsedMessage

0.69

roek

0.69

Activations Density 0.034%

phrases indicating communication or interaction requests

Follows punctuation in various contexts

prediction: Aston Villa

No Comments

No Known Activations