INDEX

Explanations

phrases indicating leadership or direction

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

 pleaſure

-0.79

Autoritní

-0.66

 faſt

-0.66

 purpoſe

-0.65

 Rina

-0.63

 leçon

-0.62

équi

-0.62

 Paulina

-0.61

tagHelper

-0.60

 Helga

-0.60

POSITIVE LOGITS

AddRange

0.67

 sosok

0.57

Mou

0.56

 ousted

0.54

❋

0.53

 IBOutlet

0.52

him

0.50

הערות

0.49

حوالہ

0.48

 charismatic

0.48

Activations Density 0.338%

phrases indicating leadership or direction

No Comments

No Known Activations