INDEX

Explanations

terms related to discussions and debates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

</i>

-0.79

но

-0.73

er

-0.71

Abp

-0.70

-0.69

Dina

-0.68

zu

-0.67

ca

-0.65

co

-0.64

POSITIVE LOGITS

debate

1.50

 debate

1.48

Debate

1.36

 Debate

1.34

 debates

1.33

 debated

1.33

 itſelf

1.33

DEB

1.29

 houſe

1.25

 myſelf

1.25

Activations Density 0.079%

terms related to discussions and debates

No Comments

No Known Activations