INDEX

Explanations

statements indicating dialogue or quotes attributed to individuals

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

 ocurrido

-0.29

 ocurrir

-0.28

 members

-0.28

 alternatives

-0.27

Pu

-0.27

čné

-0.27

 temp

-0.27

 Millennium

-0.26

 technologies

-0.26

 ویکی‌پدی

-0.25

POSITIVE LOGITS

himself

1.02

 himself

0.97

 himſelf

0.96

 Himself

0.91

 Geiſt

0.85

 zijne

0.85

 ſeiner

0.83

Efq

0.82

 ſeinen

0.81

 Menſchen

0.81

Activations Density 0.343%

statements indicating dialogue or quotes attributed to individuals

No Comments

No Known Activations