INDEX

Explanations

phrases that indicate conditionality or dependencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Horst

-0.67

 Huerta

-0.64

centralwidget

-0.64

æa

-0.62

 Gauthier

-0.61

 पत्र

-0.59

 Burch

-0.58

 çı

-0.58

peteer

-0.57

깥

-0.57

POSITIVE LOGITS

 Depends

1.38

 depends

1.36

 depending

1.30

depends

1.29

 depend

1.29

Depends

1.25

 depended

1.25

depend

1.23

depending

1.20

 depende

1.11

Activations Density 0.128%

phrases that indicate conditionality or dependencies

No Comments

No Known Activations