INDEX

Explanations

terms related to machine learning algorithms and techniques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 onOptions

-0.71

AndEndTag

-0.68

Obrázky

-0.68

Efq

-0.66

 SafeMath

-0.65

AllAfrica

-0.64

ScopeManager

-0.61

caught

-0.60

KEYCODE

-0.60

 besz

-0.60

POSITIVE LOGITS

 sklearn

0.63

keras

0.62

 trained

0.57

ivy

0.54

 training

0.54

 using

0.53

 learning

0.53

SecretKey

0.52

학

0.50

 McCle

0.48

Activations Density 0.518%

terms related to machine learning algorithms and techniques

No Comments

No Known Activations