INDEX

Explanations

technical terms and metrics related to photography

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

íncia

-0.55

vábbi

-0.53

RoutingModule

-0.52

 photographie

-0.52

 rayos

-0.50

 AssemblyTitle

-0.49

jetty

-0.49

principalColumn

-0.49

subpackage

-0.48

vânt

-0.48

POSITIVE LOGITS

ńcu

0.58

 Canon

0.56

 Yong

0.53

AF

0.53

useNewUrlParser

0.53

 autofocus

0.51

">//

0.50

CardBody

0.50

APS

0.49

 bodies

0.49

Activations Density 0.084%

technical terms and metrics related to photography

No Comments

No Known Activations