INDEX

Explanations

return statements in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Chou

-0.57

roidery

-0.56

 Chou

-0.53

eddah

-0.51

MLS

-0.50

cerv

-0.50

Bim

-0.50

 Escrow

-0.49

̍t

-0.49

entile

-0.49

POSITIVE LOGITS

return

2.21

 return

1.69

 Return

1.31

Return

1.22

 returning

1.16

 returns

1.15

 RETURN

1.12

RETURN

1.09

 Returning

1.01

 returned

0.99

Activations Density 0.049%

return statements in code snippets

No Comments

No Known Activations