INDEX

Explanations

instances of the phrase "According to"

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

Preceding "to," "the," or a country name

np_acts-logits-general · gemini-2.0-flash

According to / In phrases

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Италијани

-0.65

 Administrativna

-0.63

 Мексичка

-0.63

Rüyada

-0.60

setVerticalGroup

-0.59

 ujednoznacz

-0.55

principalColumn

-0.54

Jîn

-0.54

-------

-0.54

 Numerade

-0.53

POSITIVE LOGITS

 tää

0.44

 arcilla

0.44

 Eigentü

0.43

ussen

0.43

 lecteurs

0.43

ríamos

0.42

 elämä

0.42

 solteiro

0.41

We

0.41

yczą

0.40

Activations Density 1.348%

instances of the phrase "According to"

Preceding "to," "the," or a country name

According to / In phrases

No Comments

No Known Activations