INDEX

Explanations

terms related to loss functions and performance metrics in artificial neural networks

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InvalidProtocol

-0.67

 mathematicians

-0.58

 refusé

-0.57

 mathematician

-0.57

 MATHEMAT

-0.57

 Calculations

-0.55

 MATLAB

-0.53

 FORTRAN

-0.51

 storici

-0.51

calculations

-0.50

POSITIVE LOGITS

awaiter

0.60

 task

0.56

hoeddwyd

0.56

IVEREF

0.56

Cyfeiriadau

0.55

+#+

0.55

 оригіналу

0.55

MigrationBuilder

0.55

はじめに

0.54

انگلیسی

0.54

Activations Density 1.049%

terms related to loss functions and performance metrics in artificial neural networks

No Comments

No Known Activations