INDEX

Explanations

return statements and related function behaviors 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 @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 demais

-0.59

Dazu

-0.57

 kura

-0.55

Sä

-0.54

kuuta

-0.54

indeed

-0.53

Quién

-0.52

Somebody

-0.52

 artinya

-0.51

 Dazu

-0.50

POSITIVE LOGITS

 returns

1.22

 Return

1.22

 RETURN

1.18

 Returns

1.17

return

1.14

 返回

1.10

 return

1.09

returns

1.05

RETURN

1.04

 returned

1.04

Activations Density 0.084%

return statements and related function behaviors in code

No Comments

No Known Activations

return statements and related function behaviors in code

No Comments

No Known Activations