INDEX

Explanations

questions and phrases related to proximity or closeness

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

followed by "close" or "closer"

np_acts-logits-general · gemini-2.0-flash

achieving closeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

yntaxException

-0.66

 Normdatei

-0.66

 Simplemente

-0.62

IsMutable

-0.54

<_>

-0.54

llion

-0.52

 فريبيس

-0.50

存于互联网档案馆

-0.50

PerformLayout

-0.49

 ISNI

-0.49

POSITIVE LOGITS

 close

3.65

 Close

3.17

 closer

3.15

close

3.07

Close

2.94

 CLOSE

2.91

 closest

2.78

closer

2.64

 Closer

2.58

 closeness

2.52

Activations Density 0.603%

questions and phrases related to proximity or closeness

followed by "close" or "closer"

achieving closeness

No Comments

No Known Activations