INDEX

Explanations

references to ranges or measurements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Witkin

-0.90

 Mooney

-0.89

 Nutt

-0.84

 Eleventh

-0.83

 Hül

-0.83

 bookId

-0.81

 UITableViewCell

-0.80

 blessé

-0.79

letus

-0.78

 Kowalski

-0.78

POSITIVE LOGITS

 ranges

1.73

 range

1.65

 Range

1.59

 RANGE

1.51

ranges

1.43

 Ranges

1.42

Range

1.41

range

1.41

Ranges

1.36

RANGE

1.36

Activations Density 0.093%

references to ranges or measurements in various contexts

No Comments

No Known Activations