INDEX

Explanations

phrases indicating absence or lack of something

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

"None" followed by "of"

np_acts-logits-general · gemini-2.0-flash

none of

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Spill

-0.71

 fevere

-0.70

 ſte

-0.68

⤹

-0.67

Spill

-0.66

casio

-0.66

 ſche

-0.63

goyle

-0.63

 ſta

-0.63

 lacto

-0.62

POSITIVE LOGITS

None

0.63

 None

0.59

none

0.55

 none

0.54

 ninguno

0.48

 tercero

0.47

NONE

0.47

 NONE

0.45

のです

0.44

 zichzelf

0.43

Activations Density 0.082%

phrases indicating absence or lack of something

"None" followed by "of"

none of

No Comments

No Known Activations