INDEX

Explanations

references to instances or occurrences related to time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 asiatique

-0.70

 nationaux

-0.68

 Meksiku

-0.67

GEBURTSDATUM

-0.65

adaptiveStyles

-0.64

")));

-0.64

 panoramique

-0.64

 ivelany

-0.63

 électroniques

-0.63

 zeker

-0.62

POSITIVE LOGITS

 everytime

0.71

 whenever

0.67

([]

0.64

whenever

0.59

########.

0.57

 Burnham

0.57

Flam

0.56

 Whenever

0.54

 Flam

0.54

ׂ

0.54

Activations Density 0.217%

references to instances or occurrences related to time

No Comments

No Known Activations