INDEX

Explanations

terms related to data protection and privacy policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 nahilalakip

-1.24

parsedMessage

-1.23

oredCriteria

-1.21

aarrggbb

-1.21

GEBURTSDATUM

-1.20

 дописавши

-1.19

WithIOException

-1.18

RegistryLite

-1.14

 estekak

-1.11

SharedDtor

-1.10

POSITIVE LOGITS

<bos>

0.63

0.52

0.49

0.46

es

0.46

0.45

hi

0.45

↵

0.44

den

0.44

Activations Density 0.355%

terms related to data protection and privacy policies

No Comments

No Known Activations