INDEX

Explanations

technical terms related to GPS technology and measurements

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

 flamma

-0.66

Rüyada

-0.66

 cools

-0.63

tagext

-0.56

 embers

-0.54

eloma

-0.54

 Paglinawan

-0.53

mability

-0.52

 Clown

-0.51

 cooler

-0.51

POSITIVE LOGITS

GPS

0.83

GPS

0.69

 precision

0.65

GN

0.65

 accuracy

0.64

gps

0.63

 corrections

0.61

gps

0.60

 accurate

0.59

NAV

0.59

Activations Density 0.492%

technical terms related to GPS technology and measurements

No Comments

No Known Activations