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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

here

-0.47

of

-0.47

and

-0.47

伍

-0.44

uslar

-0.43

Hust

-0.42

Ș

-0.42

 felt

-0.42

 kurzen

-0.41

POSITIVE LOGITS

return

1.32

istoitu

1.12

 مشين

1.11

 مرئيه

1.02

ंदीखरीदारी

1.01

writerow

0.96

migrationBuilder

0.94

argout

0.93

 Returns

0.91

Personensuche

0.91

Activations Density 0.041%

return statements in code

No Comments

No Known Activations