INDEX

Explanations

structures and hierarchical formatting in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

featureID

-1.03

дцать

-0.91

endmodule

-0.84

AsUp

-0.84

PreferredItem

-0.81

 MenuView

-0.78

 EClass

-0.77

fillType

-0.74

ActiveRecord

-0.74

 calendriers

-0.74

POSITIVE LOGITS

1.74

1.42

1.39

1.35

1.30

1.26

1.24

1.20

Activations Density 0.095%

structures and hierarchical formatting in text

No Comments

No Known Activations