INDEX

Explanations

return statements 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 @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Himo

-0.54

 ""],

-0.53

 通販

-0.52

}*/

-0.52

 libr

-0.52

 Baillargeon

-0.51

bewerken

-0.51

 Italijanski

-0.51

 Hitch

-0.50

(":");

-0.49

POSITIVE LOGITS

ArgsConstructor

0.77

WithMany

0.74

UpInside

0.70

endphp

0.68

 AssemblyTitle

0.65

FlatAppearance

0.65

posedge

0.64

extAlignment

0.64

AxisAlignment

0.63

fromCharCode

0.62

Activations Density 0.046%

return statements in code

No Comments

No Known Activations