INDEX

Explanations

technical terms associated with data analysis or processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 aceea

-0.43

nyata

-0.42

 hầu

-0.40

<eos>

-0.39

 paik

-0.39

 למש

-0.39

 noted

-0.38

…

-0.37

 maris

-0.36

 сельского

-0.35

POSITIVE LOGITS

 متعلقه

0.98

sizeCache

0.93

ChildScrollView

0.92

 Offisielt

0.91

Personendaten

0.90

#+#

0.86

 للاسماء

0.86

XmlEnum

0.84

ंदीखरीदारी

0.84

tagHelperRunner

0.83

Activations Density 1.439%

technical terms associated with data analysis or processing

No Comments

No Known Activations