INDEX

Explanations

sentences expressing personal opinions and experiences

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

########.

-0.87

Hochspringen

-0.72

EndContext

-0.71

GEBURTS

-0.68

 autorytatywna

-0.67

 snippetHide

-0.65

CloseOperation

-0.65

styleType

-0.63

expandindo

-0.62

EndGlobalSection

-0.62

POSITIVE LOGITS

 kasarigan

0.70

 intress

0.61

 klara

0.53

 azonban

0.51

او

0.50

 netts

0.49

 idéia

0.48

 anderem

0.48

ंत

0.48

 viszont

0.48

Activations Density 0.246%

sentences expressing personal opinions and experiences

No Comments

No Known Activations