INDEX

Explanations

phrases related to laws or regulations

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

 inconce

-0.86

 wherea

-0.86

 excru

-0.86

 inconnu

-0.85

 indestru

-0.85

 unspeak

-0.84

 milf

-0.83

 jurassic

-0.83

 impra

-0.81

 accla

-0.81

POSITIVE LOGITS

 كومونز

0.78

Autoritní

0.61

 ideolog

0.61

 reason

0.60

way

0.59

Kein

0.59

 stoff

0.59

no

0.57

 ModelExpression

0.56

 Paglinawan

0.56

Activations Density 0.110%

phrases related to laws or regulations

No Comments

No Known Activations