INDEX

Explanations

programming comments and annotations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

transQ

-0.66

awtextra

-0.63

UnsafeEnabled

-0.57

 glabrous

-0.56

 rollers

-0.55

 Exteriores

-0.55

 Rumuni

-0.54

 neutrality

-0.54

IsMutable

-0.52

IsContent

-0.52

POSITIVE LOGITS

بوابة

0.95

 للمعارف

0.61

0.57

*>(

0.56

bcryptjs

0.55

dafx

0.54

providedIn

0.54

########.

0.54

 Deiner

0.54

asInstanceOf

0.54

Activations Density 0.174%

programming comments and annotations

No Comments

No Known Activations