INDEX

Explanations

references to direct speech or quotations

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

MessageOf

-0.63

зулта

-0.63

yntaxException

-0.59

reactstrap

-0.58

ellido

-0.57

usalem

-0.56

usda

-0.55

]--;

-0.53

erdings

-0.53

-0.52

POSITIVE LOGITS

invokeLater

0.77

 незавершена

0.66

 BorderRadius

0.63

 didReceive

0.62

Rhestr

0.57

 envers

0.56

didSet

0.55

 contextLoads

0.55

WEBPACK

0.53

 souverain

0.52

Activations Density 0.220%

references to direct speech or quotations

No Comments

No Known Activations