INDEX

Explanations

technical terms and concepts related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

elemField

-0.58

 <=",

-0.57

 polegadas

-0.54

}]

-0.53

WaitGroup

-0.53

makeText

-0.50

 препратки

-0.50

战士

-0.49

EClass

-0.48

 ferdig

-0.47

POSITIVE LOGITS

mapStateToProps

0.71

supervised

0.67

erialize

0.64

WireFormatLite

0.61

contextMenu

0.60

 disambiguazione

0.60

ffield

0.58

abases

0.56

pectives

0.56

帖最后由

0.56

Activations Density 0.029%

technical terms and concepts related to programming and software development

No Comments

No Known Activations