INDEX

Explanations

references to volumes and editions in published works

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+#

-0.74

 Pingback

-0.71

ngOnInit

-0.65

}>;

-0.63

didSet

-0.60

Билгалдахарш

-0.60

>::

-0.58

InteropServices

-0.57

tagHelper

-0.57

 ExecuteAsync

-0.56

POSITIVE LOGITS

 contiennent

0.66

 Volume

0.63

volume

0.62

 vols

0.60

 volumes

0.58

Volume

0.57

 Volumes

0.57

 Monfieur

0.57

volumes

0.57

Filmographie

0.56

Activations Density 0.024%

references to volumes and editions in published works

No Comments

No Known Activations