INDEX

Explanations

references to specific structures or forms in written content

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

"form"

np_acts-logits-general · gemini-2.0-flash

the form

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Tikang

-0.73

writeFieldEnd

-0.72

findpost

-0.72

tagHelperRunner

-0.64

?>">

-0.64

 ویکی‌پدیا

-0.64

Personendaten

-0.63

RegistryLite

-0.59

 CreateTagHelper

-0.59

 ComVisible

-0.58

POSITIVE LOGITS

 form

2.80

form

2.15

 Form

2.15

Form

1.95

 forms

1.95

 FORM

1.93

 bentuk

1.89

 vorm

1.82

 forma

1.73

 Forms

1.69

Activations Density 0.328%

references to specific structures or forms in written content

"form"

the form

No Comments

No Known Activations