INDEX

Explanations

phrases related to product descriptions and specifications, particularly focusing on features and benefits

oai_token-act-pair · gpt-3.5-turbo

phrases indicating significant or notable events or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Flavoring

-0.87

 Watergate

-0.73

APD

-0.72

ascus

-0.71

ghazi

-0.71

 constitu

-0.71

venge

-0.70

 Benghazi

-0.70

AGA

-0.69

ettel

-0.69

POSITIVE LOGITS

eaturing

0.92

 Features

0.88

itled

0.87

Setup

0.86

 Designed

0.85

Features

0.84

Instruct

0.82

Ingredients

0.81

 proceeds

0.80

 demo

0.79

Activations Density 0.755%

phrases related to product descriptions and specifications, particularly focusing on features and benefits

phrases indicating significant or notable events or experiences

No Comments

No Known Activations