INDEX

Explanations

technical terms and formulas related to machine learning algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

MigrationBuilder

-0.86

 surla

-0.62

 propOrder

-0.60

 uska

-0.56

JspWriter

-0.56

StoryboardSegue

-0.55

ngdoc

-0.55

soort

-0.55

✭✭

-0.55

 AssemblyProduct

-0.54

POSITIVE LOGITS

 DataLoader

0.74

 train

0.73

train

0.71

 training

0.67

loader

0.65

DataLoader

0.65

 loader

0.64

 validation

0.64

Train

0.63

 dataset

0.63

Activations Density 0.356%

technical terms and formulas related to machine learning algorithms

No Comments

No Known Activations