INDEX

Explanations

phrases related to announcements and notifications

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

preceding announcements or reveals

np_acts-logits-general · gemini-2.0-flash

upcoming details and announcements

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

 Winaray

-0.60

まま

-0.58

SBATCH

-0.51

ⓒ

-0.46

UIFont

-0.46

 voulons

-0.45

 podjet

-0.45

 rischio

-0.45

 Diſ

-0.44

中途

-0.43

POSITIVE LOGITS

 details

0.69

 specifics

0.69

 soon

0.69

 detail

0.68

ьаж

0.66

soon

0.65

 SOON

0.64

stateParams

0.64

detailed

0.64

Soon

0.64

Activations Density 0.245%

phrases related to announcements and notifications

preceding announcements or reveals

upcoming details and announcements

No Comments

No Known Activations