INDEX

Explanations

technical terms and references related to data repositories and software architecture

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

like

-0.52

me

-0.51

only

-0.49

not

-0.48

if

-0.48

-0.47

they

-0.47

-0.46

ft

-0.45

POSITIVE LOGITS

parsedMessage

1.03

 JpaRepository

0.94

 فريبيس

0.91

0.89

IUrlHelper

0.85

haustible

0.84

 unknownFields

0.83

QMetaType

0.80

Personensuche

0.78

 VizieR

0.78

Activations Density 1.660%

technical terms and references related to data repositories and software architecture

No Comments

No Known Activations