INDEX

Explanations

references to specific time periods or phases

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

 propOrder

-0.75

BrowserModule

-0.66

apimachinery

-0.65

})]

-0.60

énario

-0.60

Források

-0.58

'},

-0.58

']?>

-0.57

 creatinine

-0.57

")))

-0.57

POSITIVE LOGITS

 periods

1.27

 During

1.25

during

1.21

During

1.20

 during

1.16

 period

1.11

 DURING

1.08

 Periods

1.05

durante

1.03

Während

1.02

Activations Density 0.074%

references to specific time periods or phases

No Comments

No Known Activations