INDEX

Explanations

references to criminal organizations like the Mob in urban settings like Chicago

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 shenan

-0.78

 Tangerang

-0.66

 hentai

-0.62

 Covington

-0.60

 depl

-0.58

 Maldonado

-0.58

 Hamza

-0.57

 Jonathan

-0.56

 Banjar

-0.56

 suna

-0.56

POSITIVE LOGITS

Mob

1.17

Mob

1.09

mob

1.02

mob

0.93

MOB

0.83

MOB

0.81

 Mobility

0.79

Mobility

0.76

 mobility

0.72

mobility

0.66

Activations Density 0.521%

references to criminal organizations like the Mob in urban settings like Chicago

No Comments

No Known Activations