INDEX

Explanations

references to live events, especially performances and broadcasts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

rungsseite

-0.77

مراجع

-0.71

}))

-0.67

 iNdEx

-0.66

})));

-0.65

 дописавши

-0.65

RetentionPolicy

-0.64

 GetEnumerator

-0.64

ngrx

-0.64

++)

-0.63

POSITIVE LOGITS

lihood

0.92

LIVE

0.78

liest

0.75

 LIVE

0.72

lier

0.69

 Live

0.65

 live

0.63

Live

0.62

wire

0.59

live

0.57

Activations Density 0.077%

references to live events, especially performances and broadcasts

No Comments

No Known Activations