INDEX

Explanations

references to neural network architecture and design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

IntoConstraints

-0.85

+#+#

-0.82

:✨

-0.78

CloseOperation

-0.73

ंदीखरीदारी

-0.71

 nahilalakip

-0.62

 Portail

-0.60

 AssemblyVersion

-0.60



-0.59

 JpaRepository

-0.59

POSITIVE LOGITS

 network

1.00

 training

1.00

 neural

0.99

 Neural

0.89

 layer

0.88

 networks

0.86

 Training

0.85

 neurons

0.83

training

0.83

 Network

0.83

Activations Density 0.458%

references to neural network architecture and design

No Comments

No Known Activations