INDEX

Explanations

comment lines in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

'));

-0.96

EndInit

-0.85

`,

-0.80

ValueStyle

-0.78

Bronnen

-0.77

"));

-0.75

providedIn

-0.75

ymce

-0.75

createConnection

-0.74

iteln

-0.72

POSITIVE LOGITS

//

1.59

//

1.55

//

1.55

="//

1.34

);//

1.32

">//

1.31

("//

1.30

;//

1.28

,//

1.25

-//

1.24

Activations Density 0.056%

comment lines in code

No Comments

No Known Activations