INDEX

Explanations

phrases indicating uncertainty or a lack of definite knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

}}}{\

-0.70

 Pera

-0.62

 Wikimedijinoj

-0.62

nestjs

-0.59

ModelAdmin

-0.59

SELF

-0.58

astian

-0.57

 purpoſe

-0.56

DataMember

-0.54

ajuato

-0.52

POSITIVE LOGITS

 getopt

0.81

posedge

0.70

adaptiveStyles

0.61

出版年

0.61

 Selon

0.56

hability

0.56

 navideña

0.55

awakeFromNib

0.54

TypeDef

0.54

webElementXpaths

0.54

Activations Density 0.008%

phrases indicating uncertainty or a lack of definite knowledge

No Comments

No Known Activations