INDEX

Explanations

warnings and references related to safety and potential hazards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

kehren

-0.50

Litteratur

-0.49

mejores

-0.48

NSMutable

-0.46

feitura

-0.45

 verrez

-0.45

kelen

-0.45

 unpopular

-0.45

śmie

-0.44

 banner

-0.43

POSITIVE LOGITS

 accident

0.84

 Accidental

0.83

 accidents

0.82

 safety

0.80

 accidental

0.78

 Accidents

0.78

Safety

0.77

 dangerous

0.76

accident

0.75

safety

0.75

Activations Density 0.122%

warnings and references related to safety and potential hazards

No Comments

No Known Activations