INDEX

Explanations

instances where the text prompts the reader to take a focused look or examination at specific details

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

 emphat

-1.02

 perfet

-0.99

 pank

-0.99

 Quod

-0.97

 unden

-0.96

 Sén

-0.96

 milf

-0.96

 Bartholo

-0.95

 kark

-0.95

 maksi

-0.94

POSITIVE LOGITS

 look

1.15

look

1.08

 Look

1.05

Look

1.02

 looks

0.98

 LOOK

0.92

 looked

0.91

Looks

0.91

looks

0.86

 Looks

0.85

Activations Density 0.078%

instances where the text prompts the reader to take a focused look or examination at specific details

No Comments

No Known Activations

instances where the text prompts the reader to take a focused look or examination at specific details

No Comments

No Known Activations