INDEX

Explanations

references to the concept of "natural" in various contexts

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

"natural"

np_acts-logits-general · gemini-2.0-flash

naturalized, history, populations, saliva

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

Související

-0.41

fjspx

-0.38

 menik

-0.33

 свер

-0.33

뀜

-0.32

ไว

-0.30

lámpara

-0.30

rophore

-0.30

 kekinian

-0.30

Cuántos

-0.29

POSITIVE LOGITS

Natural

1.27

 Natural

1.24

NATURAL

1.19

 natural

1.17

natural

1.13

 NATURAL

1.12

 naturale

0.99

naturally

0.99

 naturally

0.97

自然

0.96

Activations Density 0.104%

references to the concept of "natural" in various contexts

"natural"

naturalized, history, populations, saliva

No Comments

No Known Activations