INDEX

Explanations

non-alphanumeric symbols or formatting indicators

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

stylers

-0.69

 sessionFactory

-0.66

liosis

-0.65

nonatomic

-0.65

 insuffisamment

-0.64

 ddelweddau

-0.63

:✨

-0.62

ControllerAdvice

-0.62

 nargin

-0.61

\{\\

-0.60

POSITIVE LOGITS

ьаж

0.62

 Италијани

0.54

-------------</

0.54

Referencie

0.53

庁

0.53

Controllo

0.50

HOSTS

0.50

Odkazy

0.48

MAXN

0.47

 special

0.45

Activations Density 0.380%

non-alphanumeric symbols or formatting indicators

No Comments

No Known Activations