INDEX

Explanations

terms and phrases related to technology, particularly in the context of apps, security, and online privacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 NSCoder

-1.11

UnusedPrivate

-1.08

InjectAttribute

-1.05

tagHelperRunner

-1.05

IsMutable

-1.04

 protoimpl

-1.02

 للاسماء

-1.00

 مشين

-0.99

')))

-0.97

LookAnd

-0.97

POSITIVE LOGITS

enumi

0.56

νι

0.53

 Перейти

0.52

ưới

0.45

яз

0.45

LOYE

0.45

 Hanne

0.44

いえば

0.43

findUser

0.42

PLICATION

0.42

Activations Density 3.752%

terms and phrases related to technology, particularly in the context of apps, security, and online privacy

No Comments

No Known Activations