INDEX

Explanations

requests or commands for action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.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

NCP

-0.52

PDS

-0.48

 mountain

-0.45

GSC

-0.45

 Mountain

-0.44

 Component

-0.43

ICM

-0.43

 Karak

-0.43

 talon

-0.43

imedes

-0.42

POSITIVE LOGITS

please

0.92

Please

0.90

 please

0.88

 Please

0.86

PLEASE

0.77

 Bitte

0.76

Bitte

0.75

 PLEASE

0.73

 bitte

0.67

 Kindly

0.64

Activations Density 0.052%

requests or commands for action

No Comments

No Known Activations