INDEX

Explanations

phrases related to specific awards or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ItemBackground

-0.68

XmlAccessorType

-0.66

当時は

-0.62

 BoxDecoration

-0.56

SharedDtor

-0.55

当時

-0.54

fileID

-0.49

 fewer

-0.48

 minori

-0.47

IConfiguration

-0.47

POSITIVE LOGITS

 latest

1.30

 newest

1.08

latest

1.02

 LATEST

0.99

 Latest

0.88

Latest

0.86

 neuesten

0.86

 upcoming

0.86

newest

0.84

 cutest

0.84

Activations Density 0.322%

phrases related to specific awards or events

No Comments

No Known Activations