INDEX

Explanations

words related to technology, specifically focusing on connectivity and data

oai_token-act-pair · gpt-3.5-turbo

conjunctions and their usage in connecting ideas

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Shiva

-0.73

 Shutterstock

-0.68

 Ruler

-0.68

 Schumer

-0.66

 Fiesta

-0.66

 Cyrus

-0.65

PsyNetMessage

-0.65

$$$$

-0.65

 Staples

-0.65

eda

-0.64

POSITIVE LOGITS

rogens

1.26

rogen

1.21

 consequential

0.84

nam

0.84

 unconventional

0.83

 imaginative

0.80

non

0.79

 experimental

0.79

leans

0.78

 nons

0.77

Activations Density 0.187%

words related to technology, specifically focusing on connectivity and data

conjunctions and their usage in connecting ideas

No Comments

No Known Activations