INDEX

Explanations

phrases related to being sure, being well-rested, and having a strong foundation

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Juf

-1.38

 increa

-1.29

 inev

-1.25

 reluct

-1.22

 maneu

-1.19

 fortn

-1.19

 wherea

-1.18

 volunte

-1.18

 Augu

-1.16

 erad

-1.15

POSITIVE LOGITS

 properly

0.86

 correct

0.80

 correctly

0.76

 proper

0.73

 adequate

0.71

 ensure

0.68

 adequately

0.67

 appropriate

0.66

correct

0.62

 sufficient

0.62

Activations Density 0.291%

phrases related to being sure, being well-rested, and having a strong foundation

No Comments

No Known Activations