INDEX

Explanations

references to groups or categories of individuals or items

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

"Each" followed by a noun

np_acts-logits-general · gemini-2.0-flash

each followed by a noun

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

 anything

-0.46

li

-0.43

(!(

-0.42

 never

-0.42

 hiç

-0.41

never

-0.41

//

-0.41

追

-0.40

kot

-0.40

INO

-0.40

POSITIVE LOGITS

 individually

1.31

 câte

1.24

 separately

1.23

 each

1.03

 Each

1.01

 einzeln

0.99

 independently

0.99

Each

0.98

 EACH

0.96

each

0.95

Activations Density 0.338%

references to groups or categories of individuals or items

"Each" followed by a noun

each followed by a noun

No Comments

No Known Activations