INDEX

Explanations

assertions or declarative statements about facts or opinions

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

"That" followed by a verb

np_acts-logits-general · gemini-2.0-flash

that is, that said, that doesn't

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

 мәкал

-0.69

Datuak

-0.62

بوابة

-0.54

))){

-0.54

جوايز

-0.53

]`

-0.52

 useAuth

-0.51

所示

-0.51

 dagegen

-0.51

'])){

-0.50

POSITIVE LOGITS

ंदीखरीदारी

0.80

0.72

出版年

0.70

 wireType

0.68

AddTagHelper

0.66

 '\\;'

0.63

ThroughAttribute

0.62

writeFieldEnd

0.62

 متعلقه

0.60

contentLoaded

0.59

Activations Density 0.077%

assertions or declarative statements about facts or opinions

"That" followed by a verb

that is, that said, that doesn't

No Comments

No Known Activations