INDEX

Explanations

structured data and formal definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Jeografia

-0.45

Kaynakça

-0.44

 generally

-0.42

이터

-0.41

 vois

-0.40

he

-0.39

dam

-0.38

unit

-0.38

ung

-0.37

 diper

-0.37

POSITIVE LOGITS

ImageContext

0.78

сылкі

0.75

 Wiktionnaire

0.74

 ſtand

0.73

dafx

0.72

最快更新

0.71

roek

0.69

 ſte

0.69

存于互联网档案馆

0.67

StoryboardSegue

0.67

Activations Density 0.081%

structured data and formal definitions

No Comments

No Known Activations