INDEX

Explanations

references to artificial neural networks (ANNs) and techniques in machine learning

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

AndEndTag

-0.77

Efq

-0.69

 onOptions

-0.62

 imageNamed

-0.62

بوابة

-0.61

 sauvages

-0.61

ElementException

-0.60

 jScrollPane

-0.59

 SafeMath

-0.59

 ویکی‌پدیای

-0.59

POSITIVE LOGITS

keras

0.69

 trained

0.63

 learning

0.61

 keras

0.60

 training

0.60

openConnection

0.57

Regressor

0.56

 sklearn

0.56

 tensorflow

0.55

SecretKey

0.54

Activations Density 0.553%

references to artificial neural networks (ANNs) and techniques in machine learning

No Comments

No Known Activations