INDEX

Explanations

phrases indicating functionality and effectiveness

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

orianCalendar

-0.69

 للمعارف

-0.68

IntoConstraints

-0.68

 Montagu

-0.63

Agora

-0.62

 Skor

-0.62

__*/

-0.61

olyte

-0.60

<>("

-0.60

)։

-0.58

POSITIVE LOGITS

 works

1.03

 Works

0.91

 funktioniert

0.90

Works

0.89

 WORKS

0.88

works

0.87

 fungerar

0.85

 fungerer

0.84

 worked

0.82

 funguje

0.82

Activations Density 0.152%

phrases indicating functionality and effectiveness

No Comments

No Known Activations