INDEX

Explanations

abbreviations and initialisms, particularly those associated with authors or specific studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

<bos>

-0.63

 linkovi

-0.62

 Wikimedijinoj

-0.56

 poveznice

-0.52

 للاسماء

-0.51

تفصیلات

-0.51

Personensuche

-0.50

LinkId

-0.49

AlterField

-0.47

 MonoBehaviour

-0.46

POSITIVE LOGITS

 homozygous

0.62

 Pembangunan

0.61

AsUp

0.59

amaño

0.57

 nakalista

0.55

 myſelf

0.53

Szk

0.53

glise

0.52

raszam

0.52

lgari

0.52

Activations Density 0.212%

abbreviations and initialisms, particularly those associated with authors or specific studies

No Comments

No Known Activations