INDEX

Explanations

references to studies and reports by multiple authors

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

uxxxx

-0.69

aarrggbb

-0.67

ViewFeatures

-0.64

 géographie

-0.56

XMLSchema

-0.49

Géographie

-0.48

Abitanti

-0.48

 Վերցված

-0.48

atste

-0.48

Gravity

-0.47

POSITIVE LOGITS

 Treue

0.61

BeginContext

0.59

XmlAccessorType

0.56

enderror

0.56

 أعلام

0.56

 conjoint

0.52

<bos>

0.52

})}

0.51

apiKey

0.51

évaluateur

0.51

Activations Density 1.098%

references to studies and reports by multiple authors

No Comments

No Known Activations