INDEX

Explanations

numerical values, specifically those representing measurements or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

-0.70

-0.68

-0.67

-0.66

-0.65

-0.64

-0.63

is

-0.62

</strong>

-0.59

POSITIVE LOGITS

 twenty

2.57

 thirty

2.56

 forty

2.46

twenty

2.46

 Twenty

2.44

 fifty

2.41

 Thirty

2.40

 sixty

2.37

 eighty

2.33

 seventy

2.31

Activations Density 0.088%

numerical values, specifically those representing measurements or quantities

No Comments

No Known Activations