INDEX

Explanations

technical terms and functions related to image processing and coordinate transformations

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

cshtml

-0.42

 тер

-0.42

fabs

-0.41

 belts

-0.40

↵

-0.39

CGContext

-0.39

-0.38

argmax

-0.38

 FormGroup

-0.38

POSITIVE LOGITS

хьтан

0.94

MLLoader

0.93

tagHelperRunner

0.81

 Савезне

0.78

 kasarigan

0.75

TypedDataSet

0.74

 مشين

0.73

)))));

0.73

XmlAccessType

0.73

SequentialGroup

0.72

Activations Density 0.109%

technical terms and functions related to image processing and coordinate transformations

No Comments

No Known Activations