INDEX

Explanations

numerical codes and identifiers related to datasets and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 FetchType

-0.55

SharedDtor

-0.55

tanleria

-0.51

idends

-0.50

 Logistics

-0.50

езда

-0.49

AddHtmlAttribute

-0.48

 стре

-0.46

enterOuterAlt

-0.46

Autowired

-0.46

POSITIVE LOGITS

 InputDecoration

0.84

InputBorder

0.73

følgelig

0.60

lapsingToolbar

0.58

ValueGeneration

0.57

findpost

0.56

maketitle

0.56

 ModelExpression

0.55

Alguna

0.55

URLException

0.54

Activations Density 0.064%

numerical codes and identifiers related to datasets and publications

No Comments

No Known Activations