INDEX

Explanations

announcements or updates provided in a written format

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

 🤣🤣

-0.59

Xoxo

-0.55

 peppa

-0.55

 snapback

-0.55

 swarovski

-0.54

 🥲

-0.54

Hahah

-0.53

 lexus

-0.53

 👍🏻

-0.53

 ❤️❤️

-0.52

POSITIVE LOGITS

SourceChecksum

0.73

Datuak

0.68

PerformLayout

0.59

 Abbé

0.57

IUrlHelper

0.56

parsedMessage

0.54

richTextPanel

0.52

Läh

0.52

expandindo

0.52

Jeografia

0.51

Activations Density 0.905%

announcements or updates provided in a written format

No Comments

No Known Activations