INDEX

Explanations

references to data model fields and generator-related terms 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 @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

licet

-0.66

Discography

-0.65

 AssemblyVersion

-0.63

ajā

-0.59

 interest

-0.57

Lähteet

-0.56

 Estatal

-0.56

wpi

-0.55

 Gianni

-0.54

◜

-0.54

POSITIVE LOGITS

 Generator

1.79

generator

1.76

 generator

1.71

Generator

1.64

 generators

1.62

 Generators

1.60

generators

1.45

Generators

1.32

 ResponseEntity

1.02

 génér

0.88

Activations Density 0.011%

references to data model fields and generator-related terms in programming

No Comments

No Known Activations

references to data model fields and generator-related terms in programming

No Comments

No Known Activations