INDEX

Explanations

instances where the word "this" is followed by other words with varied activations

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

 venice

-1.36

 eiffel

-1.33

 jurassic

-1.30

 autunno

-1.30

 riviera

-1.29

 toledo

-1.26

 stockholm

-1.24

 parteci

-1.22

 outlander

-1.21

 sappi

-1.20

POSITIVE LOGITS

 case

0.85

 particular

0.79

 instance

0.79

 context

0.78

 regard

0.77

case

0.71

 scenario

0.71

 situation

0.70

 example

0.67

 manner

0.67

Activations Density 0.096%

instances where the word "this" is followed by other words with varied activations

No Comments

No Known Activations