INDEX

Explanations

references to companies or corporations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Komunikasi

-0.77

 sorpresas

-0.69

 itſelf

-0.68

 Grüsse

-0.68

 aislado

-0.66

 Keuangan

-0.65

 Italij

-0.65

 isolada

-0.65

 Económica

-0.64

 aislada

-0.63

POSITIVE LOGITS

Pre

0.71

Co

0.67

 Dual

0.66

 Post

0.66

 Super

0.64

 lack

0.63

Fal

0.63

 Null

0.62

Un

0.61

 null

0.60

Activations Density 0.415%

references to companies or corporations

No Comments

No Known Activations