INDEX

Explanations

interactions that highlight emotional or relatable experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

GenerationType

-0.54

исленность

-0.52

XmlAccessorType

-0.52

IBarButtonItem

-0.51

WriteTagHelper

-0.50

featureID

-0.48

愷

-0.48

 fieldNum

-0.46

 kasarigan

-0.44

cstring

-0.44

POSITIVE LOGITS

 they

3.58

 mereka

3.11

They

2.94

他們

2.83

 They

2.80

 loro

2.69

他们

2.67

 они

2.63

 Mereka

2.61

they

2.59

Activations Density 6.377%

interactions that highlight emotional or relatable experiences

No Comments

No Known Activations