INDEX

Explanations

words or phrases that indicate negation or absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Autoritní

-0.69

出版年

-0.68

()?;

-0.68

 SwiftUI

-0.63

RuleContext

-0.62

 bellows

-0.60

MemoryWarning

-0.59

 LoggerFactory

-0.59

 zvuky

-0.58

 وتسجيلات

-0.58

POSITIVE LOGITS

un

2.46

Un

2.32

unt

2.28

Un

2.11

 unre

2.07

Uns

2.07

uns

2.00

Unt

1.98

Uns

1.88

UN

1.88

Activations Density 0.147%

words or phrases that indicate negation or absence

No Comments

No Known Activations