INDEX

Explanations

phrases related to rules, regulations, and authorities

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

 utop

-0.98

 franz

-0.97

 herre

-0.95

 marte

-0.94

 monaster

-0.93

 ananas

-0.91

 vinil

-0.91

 poliester

-0.90

 dises

-0.89

 artig

-0.89

POSITIVE LOGITS

are

0.88

 aren

0.77

 were

0.74

 belong

0.73

 weren

0.72

 themselves

0.70

They

0.69

THEY

0.69

they

0.68

 they

0.68

Activations Density 0.216%

phrases related to rules, regulations, and authorities

No Comments

No Known Activations