INDEX

Explanations

phrases and structures that indicate comparative or relational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 betweenstory

-0.91

 wikipagina

-0.85

 tartalomajánló

-0.78

 leprosy

-0.75

 JAXBElement

-0.74

 Chaldean

-0.73

MDS

-0.70

 dredge

-0.70

 Viper

-0.69

 NSCoder

-0.69

POSITIVE LOGITS

no

0.64

0.57

 있으며

0.57

 major

0.57

wijl

0.56

 having

0.55

 prič

0.55

iendo

0.54

 most

0.52

 notable

0.52

Activations Density 0.190%

phrases and structures that indicate comparative or relational contexts

No Comments

No Known Activations