INDEX

Explanations

technical or programming-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

cherichia

-0.52

antd

-0.48

mosis

-0.41

 pathways

-0.40

 ujednoznacz

-0.39

levard

-0.39

hydrates

-0.39

Haupt

-0.39

InputModule

-0.38

ściej

-0.38

POSITIVE LOGITS

end

1.26

 ending

1.13

 ends

1.07

End

1.07

End

1.07

 Ends

1.05

 Ending

1.03

end

1.02

 endpoints

0.98

 boundaries

0.98

Activations Density 0.574%

technical or programming-related terminology

No Comments

No Known Activations