INDEX

Explanations

keywords related to conditions, requirements, or characteristics related to plans or proposals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Personendaten

-0.79

findpost

-0.74

GenerationType

-0.72

 Antara

-0.69

ArgsConstructor

-0.68

CloseOperation

-0.67

parsedMessage

-0.67

новниш

-0.65

UnknownFieldSet

-0.63

 kasarigan

-0.62

POSITIVE LOGITS

 whatsoever

1.36

 imaginable

1.13

 anywhere

1.03

 anyone

0.99

anything

0.97

 anything

0.97

 apapun

0.96

 anybody

0.95

 conceivable

0.94

 ANYTHING

0.93

Activations Density 0.288%

keywords related to conditions, requirements, or characteristics related to plans or proposals

No Comments

No Known Activations