INDEX

Explanations

specific vehicle names or models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Normdatei

-0.73

الإنجليزية

-0.68

Rhestr

-0.65

MigrationBuilder

-0.63

enumi

-0.62

########.

-0.61

 Meksiku

-0.61

 Dicapai

-0.60

.*")]

-0.59

</tfoot>

-0.57

POSITIVE LOGITS

 hatchback

0.80

 sedan

0.75

 hatch

0.75

 station

0.74

 Hatch

0.73

 Wagon

0.71

 wagon

0.70

 coupe

0.68

 Coupe

0.65

Hatch

0.65

Activations Density 0.181%

specific vehicle names or models

No Comments

No Known Activations