INDEX

Explanations

references to specific products, items, or measurements, particularly in scientific or technical contexts

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

 AssemblyCulture

-0.83

دانشنامهٔ

-0.82

InputBorder

-0.78

yntaxException

-0.74

 BorderSide

-0.67

 Aqueous

-0.67

RectangleBorder

-0.67

 ComVisible

-0.67

parsedMessage

-0.67

Portale

-0.67

POSITIVE LOGITS

 आइटम

0.62

টি

0.51

RegressionTest

0.51

 ddelweddau

0.50

 product

0.50

}{*}{}

0.50

Product

0.48

 này

0.48

 okuyayım

0.48

自体は

0.47

Activations Density 1.257%

references to specific products, items, or measurements, particularly in scientific or technical contexts

No Comments

No Known Activations