INDEX

Explanations

terms related to image processing and retrieval in technology contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 sense

-0.29

vast

-0.29

 motor

-0.29

 jornada

-0.28

 enriched

-0.28

 committed

-0.27

 высокого

-0.26

tagext

-0.25

 Förder

-0.25

 Sense

-0.25

POSITIVE LOGITS

adaptiveStyles

0.79

 Infórmanos

0.74

 nahilalakip

0.73

+#+

0.72

 ujednoznacz

0.72

RenderAtEndOf

0.71

省市镇

0.69

BASEPATH

0.68

AISSEE

0.67

 EconPapers

0.66

Activations Density 2.852%

terms related to image processing and retrieval in technology contexts

No Comments

No Known Activations