INDEX

Explanations

technical terms and concepts related to software, especially in the context of machine learning and image recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

AccessFile

-0.70

StoryboardSegue

-0.69

rrggbb

-0.65

ाहरण

-0.64

Obrázky

-0.64

 թվական

-0.61

PMailer

-0.61

 kasarigan

-0.61

Distribuzione

-0.60

ORETICAL

-0.57

POSITIVE LOGITS

识

0.45

mo

0.44

 detecting

0.44

praw

0.43

 Kinect

0.43

addOn

0.42

OCR

0.41

He

0.41

IVI

0.41

 Jolly

0.41

Activations Density 0.392%

technical terms and concepts related to software, especially in the context of machine learning and image recognition

No Comments

No Known Activations