INDEX

Explanations

phrases related to taking action and measures for protection or prevention

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AutoField

-0.62

 useHistory

-0.59

bufio

-0.53

alamus

-0.51

 lands

-0.50

役所

-0.50

 bashing

-0.49

 orgasm

-0.49

stagland

-0.48

 experience

-0.48

POSITIVE LOGITS

 measures

1.00

Measures

0.98

 Measures

0.96

 Efforts

0.95

 efforts

0.94

 precaution

0.92

措施

0.91

 precautions

0.91

measures

0.86

efforts

0.85

Activations Density 0.198%

phrases related to taking action and measures for protection or prevention

No Comments

No Known Activations