INDEX

Explanations

terms related to metrics and evaluations 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 @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 kasarigan

-0.64

 oprot

-0.61

StoryboardSegue

-0.58

stalgia

-0.54

binant

-0.54

loem

-0.54

 unvaccinated

-0.53

AccessFile

-0.52

oprecip

-0.52

ombic

-0.52

POSITIVE LOGITS

 recognition

0.62

 detecting

0.60

 detection

0.59

 recognizing

0.56

 identification

0.55

OCR

0.54

 identifying

0.54

 rozpo

0.54

Dete

0.52

 Detection

0.52

Activations Density 0.554%

terms related to metrics and evaluations in image processing

No Comments

No Known Activations