INDEX

Explanations

references to accessibility

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

PreferredItem

-0.93

 HasFactory

-0.81

Piv

-0.80

Bix

-0.80

 Bort

-0.79

发表于

-0.79

 Volga

-0.78

urlpatterns

-0.78

coroutines

-0.77

Colt

-0.77

POSITIVE LOGITS

 accessible

1.64

accessible

1.61

 Accessible

1.45

 accessibility

1.32

accessibility

1.30

Accessible

1.29

 accessibles

1.22

 accesibles

1.20

 Accessibility

1.17

Accessibility

1.16

Activations Density 0.092%

references to accessibility

No Comments

No Known Activations