INDEX

Explanations

multiple return statements in code documentation or functional descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Мексичка

-0.76

!("{

-0.62

ronpa

-0.58

ecore

-0.57

 referenties

-0.57

---*/

-0.56

 GenerationType

-0.56

iD

-0.56

sepeda

-0.56

 PublicKey

-0.56

POSITIVE LOGITS

return

1.27

IsContent

0.79

GOTREF

0.71

 return

0.69

 ritorno

0.66

 judiciales

0.63

 partecipazione

0.62

 дописавши

0.61

__':

0.61

__":

0.60

Activations Density 0.072%

multiple return statements in code documentation or functional descriptions

No Comments

No Known Activations