INDEX

Explanations

terms related to constant definitions and properties in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 ModelExpression

-1.15

 Monfieur

-0.93

wiſe

-0.88

 MainAxisSize

-0.87

 myſelf

-0.87

 itſelf

-0.85

 GenerationType

-0.84

 Houſe

-0.83

 Majefty

-0.82

 Orrell

-0.82

POSITIVE LOGITS

Lähteet

0.51

rawDesc

0.51

Kaynakça

0.51

Collegamenti

0.50

Notae

0.49

참고

0.48

 références

0.47

 final

0.47

 Schmitz

0.46

ges

0.46

Activations Density 0.030%

terms related to constant definitions and properties in programming

No Comments

No Known Activations