INDEX

Explanations

phrases indicating location or position within a narrative

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

Following "in" or preposition

np_acts-logits-general · gemini-2.0-flash

in front

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

autique

-0.61

Jeografia

-0.58

setVerticalGroup

-0.57

 SwitchCompat

-0.56

 समीक्षाओं

-0.54

nationality

-0.53

 mergeFrom

-0.53

 MenuView

-0.53

 للاسماء

-0.53

transQ

-0.52

POSITIVE LOGITS

 المعيارى

0.58

 useSelector

0.56

//

0.53

VIAF

0.53

oneof

0.53

 dihasilkan

0.52

__(/*!

0.51

nestjs

0.51

exitRule

0.50

weig

0.50

Activations Density 0.152%

phrases indicating location or position within a narrative

Following "in" or preposition

in front

No Comments

No Known Activations