INDEX

Explanations

sentences that describe relationships or connections between characters or entities

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

 estekak

-0.70

 الحره

-0.59

awaiter

-0.56

IsMutable

-0.51

TypedDataSet

-0.50

menistan

-0.48

protoc

-0.46

 corporate

-0.46

 gradova

-0.46

</tfoot>

-0.45

POSITIVE LOGITS

spesies

0.67

 Theſe

0.64

Efq

0.63

idiary

0.60

Distribución

0.57

eseorang

0.57

ſy

0.55

 bogor

0.55

شكرا

0.54

 MenuView

0.53

Activations Density 0.271%

sentences that describe relationships or connections between characters or entities

No Comments

No Known Activations