INDEX

Explanations

passive constructions and references to making or rendering something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

دانشنامهٔ

-0.63

>[]

-0.61

tvguidetime

-0.59

 Biôgrafia

-0.58

usp

-0.56

DispatchToProps

-0.55

ValueStyle

-0.55

timb

-0.55

 Camar

-0.54

Tembelea

-0.53

POSITIVE LOGITS

évaluateur

0.70

setopt

0.67

setVerticalGroup

0.64

InjectMocks

0.64

opsida

0.61

 indisponible

0.59

endphp

0.59

 препратки

0.56

rendered

0.54

 render

0.54

Activations Density 0.288%

passive constructions and references to making or rendering something

No Comments

No Known Activations