INDEX

Explanations

phrases indicating necessity or requirement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

]")]

-0.66

onOptions

-0.60

Kini

-0.59

WORTH

-0.57

 Realms

-0.56

 contextLoads

-0.53

tellungs

-0.53

Illust

-0.53

 autrefois

-0.53

mapStateToProps

-0.52

POSITIVE LOGITS

 must

0.91

要有

0.80

must

0.77

Must

0.75

 MUST

0.73

 debe

0.72

Debe

0.71

 Must

0.69

 Debe

0.68

zzleHttp

0.67

Activations Density 0.286%

phrases indicating necessity or requirement

No Comments

No Known Activations