INDEX

Explanations

references to clothing and sewing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

GEBURTSDATUM

-0.99

Portail

-0.98

 AssemblyCulture

-0.94

</tfoot>

-0.89

XtraReports

-0.87

 craters

-0.85

 <<<<<<<<<<<<<<

-0.79

 tunneling

-0.78

 lenker

-0.78

참고

-0.76

POSITIVE LOGITS

 clothes

2.92

 Clothes

2.58

clothes

2.39

Clothes

2.38

 clothing

2.38

 Clothing

2.06

clothing

1.94

 CLOTH

1.93

Clothing

1.83

 clothe

1.80

Activations Density 0.050%

references to clothing and sewing

No Comments

No Known Activations