INDEX

Explanations

content related to Jewish and Latino communities

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

 saluti

-0.65

 abiti

-0.65

 sogni

-0.64

 lapto

-0.63

 auguri

-0.61

 pensieri

-0.61

 affez

-0.60

 salade

-0.58

 parlando

-0.57

 vestiti

-0.56

POSITIVE LOGITS

 unspeak

0.98

 Intere

0.98

 Daven

0.94

 Glou

0.93

 Bartholo

0.90

 reluct

0.90

Juf

0.90

 indescri

0.89

 gaily

0.88

 homeward

0.86

Activations Density 0.892%

content related to Jewish and Latino communities

No Comments

No Known Activations