INDEX

Explanations

expressions of hope and assistance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

-0.41

-0.40

 fine

-0.38

老

-0.38

·

-0.37

tan

-0.37

von

-0.37

-0.36

POSITIVE LOGITS

Datuak

1.23

Personendaten

1.12

 myſelf

0.96

 NSCoder

0.92

 Theſe

0.90

 itſelf

0.85

 مشين

0.85

 ainfi

0.84

AndEndTag

0.82

以上就是

0.81

Activations Density 0.247%

expressions of hope and assistance

No Comments

No Known Activations