INDEX

Explanations

terms related to transparency in financial and political contexts

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

 reluct

-1.89

 disagre

-1.85

 impra

-1.84

 accla

-1.82

 increa

-1.80

 shenan

-1.76

 indestru

-1.73

 emphat

-1.73

 volunte

-1.71

 guarante

-1.68

POSITIVE LOGITS

 transparency

1.49

 transparent

1.41

transparent

1.26

transparency

1.21

Transparent

1.20

Transparency

1.19

 Transparency

1.15

 Transparent

1.04

透明

1.01

 transparente

0.92

Activations Density 0.077%

terms related to transparency in financial and political contexts

No Comments

No Known Activations