INDEX

Explanations

terms related to making arrangements or plans

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 helse

-0.83

djangoproject

-0.83

 reação

-0.81

MediaStore

-0.81

 strøm

-0.78

endphp

-0.75

艸

-0.74

 critique

-0.73

 AssemblyCulture

-0.72

itzender

-0.71

POSITIVE LOGITS

 ARRANG

1.10

 Arrangements

1.08

arrange

1.07

 arrangements

1.07

Arrangements

1.02

 Arrangement

0.99

 defaultstate

0.98

 arrange

0.95

 Arrange

0.89

 arranged

0.89

Activations Density 0.136%

terms related to making arrangements or plans

No Comments

No Known Activations