INDEX

Explanations

phrases that indicate conditions or characteristics associated with different subjects or entities

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

"which" followed by a verb

np_acts-logits-general · gemini-2.0-flash

which followed by a verb

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

SharedDtor

-0.53

 ujednoznacz

-0.53

testens

-0.51

Portale

-0.49

sá

-0.49

})*/

-0.49

 Manns

-0.49

 defStyle

-0.49

fastjson

-0.48

 gravity

-0.47

POSITIVE LOGITS

transQ

0.66

didSet

0.65

 whereof

0.65

 defaultstate

0.63

Jeografia

0.61

 wireType

0.61

argout

0.58

 dimana

0.58

ributions

0.57

ppuden

0.57

Activations Density 0.238%

phrases that indicate conditions or characteristics associated with different subjects or entities

"which" followed by a verb

which followed by a verb

No Comments

No Known Activations