INDEX

Explanations

different classes or types of icons and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ագրություններ

-1.07

 كومونز

-0.96

InputBorder

-0.93

 فريبيس

-0.92

 propOrder

-0.91

 BoxFit

-0.91

DrawerToggle

-0.90

ſelf

-0.89

 دیکھیے

-0.87

<?>>

-0.87

POSITIVE LOGITS

Fa

1.37

fa

1.28

fa

1.22

Fa

1.14

 Faulkner

1.10

FA

1.07

FA

0.99

faults

0.81

 Faul

0.78

Faz

0.77

Activations Density 0.168%

different classes or types of icons and symbols

No Comments

No Known Activations