INDEX

Explanations

references to electronic devices, especially laptops

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.89

 encomp

-1.07

/**

-1.02

 cushi

-1.01

 intersper

-0.98

 hairc

-0.97

 affor

-0.93

<?

-0.93

 unspeak

-0.93

 milf

-0.93

POSITIVE LOGITS

 laptop

1.19

Lap

1.09

lap

1.06

Lap

1.06

lap

1.04

 Laptop

1.03

 laptops

1.03

Laptop

1.00

laptop

0.98

LAP

0.90

Activations Density 0.237%

references to electronic devices, especially laptops

No Comments

No Known Activations