INDEX

Explanations

references to beta testing and reviews related to software or products

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tvguidetime

-0.61

AutoresizingMask

-0.58

 tartalomajánló

-0.58

)))));

-0.56

 ModelExpression

-0.54

MessageTagHelper

-0.52

 gelang

-0.51

]))

-0.51

}))

-0.50

 Betis

-0.50

POSITIVE LOGITS

 preview

0.91

SourceChecksum

0.86

 previews

0.76

Preview

0.76

 Preview

0.74

preview

0.71

 sneak

0.65

 draft

0.62

 PREVIEW

0.62

 sample

0.61

Activations Density 0.351%

references to beta testing and reviews related to software or products

No Comments

No Known Activations