INDEX

Explanations

references to physical elements or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 doubtnut

-1.21

LookAnd

-1.16

 myſelf

-1.14

 ་་

-1.10

 Houſe

-1.09

 Cæsar

-1.09

 photolibrary

-1.07

 Jefus

-1.07

WebVitals

-1.06

 ―――――

-1.05

POSITIVE LOGITS

phys

0.80

“

0.74

0.73

 physical

0.71

 above

0.69

the

0.69

con

0.68

 next

0.67

 physically

0.66

‘

0.66

Activations Density 0.204%

references to physical elements or characteristics

No Comments

No Known Activations