INDEX

Explanations

technical terms related to computer hacking and forensics

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

 makro

-1.00

 parati

-0.99

 behar

-0.96

 hina

-0.95

 Kategor

-0.94

 teras

-0.91

 antik

-0.90

buk

-0.89

 utop

-0.89

 kule

-0.89

POSITIVE LOGITS

 unspeak

0.98

 indescri

0.92

 tolerably

0.89

 ecru

0.83

 loveliness

0.81

 shenan

0.78

 endeavouring

0.77

 gaily

0.76

 perchance

0.75

 vainly

0.74

Activations Density 0.169%

technical terms related to computer hacking and forensics

No Comments

No Known Activations