INDEX

Explanations

terms and concepts related to keypoint detection and descriptor evaluation in image processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

SerializedSize

-0.51

tå

-0.50

solids

-0.50

jooq

-0.49

erre

-0.48

 pulumi

-0.47

放大

-0.46

Pratique

-0.46

pozorn

-0.45

Obrázky

-0.45

POSITIVE LOGITS

nlp

0.65

 ujednoznacz

0.63

NLP

0.60

NLP

0.59

 Newswire

0.59

Newswire

0.58

 Infórmanos

0.57

Попис

0.56

JsonKey

0.55

 nltk

0.55

Activations Density 0.961%

terms and concepts related to keypoint detection and descriptor evaluation in image processing

No Comments

No Known Activations