INDEX

Explanations

phrases related to laws and regulations, as well as medical symptoms and treatments

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

<bos>

-2.02

 intersper

-1.02

 disbur

-0.95

/***

-0.89

ⓧ

-0.88

 endow

-0.86

 adjour

-0.84

 defray

-0.83

/**

-0.81

-0.79

POSITIVE LOGITS

 montagna

0.90

 kebaya

0.89

 bandung

0.84

 croce

0.80

 asado

0.77

 bicic

0.77

 thuy

0.76

 frito

0.75

 Jambi

0.74

 jawa

0.74

Activations Density 8.344%

phrases related to laws and regulations, as well as medical symptoms and treatments

No Comments

No Known Activations