INDEX

Explanations

statistical data and percentages pertaining to demographics and economic indicators

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

 Yugos

-0.64

 hentai

-0.63

 witcher

-0.61

 pegasus

-0.61

 madonna

-0.60

 befo

-0.60

 „,

-0.60

 milf

-0.60

……"

-0.59

 pixar

-0.58

POSITIVE LOGITS

 karton

0.75

 silikon

0.70

 kristal

0.65

 vertik

0.65

 konkre

0.64

 seksi

0.63

 akut

0.63

 protokol

0.62

 abstrak

0.60

(">>

0.59

Activations Density 0.099%

statistical data and percentages pertaining to demographics and economic indicators

No Comments

No Known Activations