INDEX

Explanations

instances of the word "more."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bufio

-0.79

 Cluj

-0.78

 IntelliJ

-0.73

/**

-0.72

 Cæsar

-0.72

 jScrollPane

-0.71



-0.70

 acacia

-0.70

daß

-0.70

 blessés

-0.68

POSITIVE LOGITS

 more

2.74

more

2.14

 MORE

2.11

 More

2.06

More

2.01

MORE

1.78

 lebih

1.45

 más

1.41

 mehr

1.39

 less

1.30

Activations Density 0.112%

instances of the word "more."

No Comments

No Known Activations