INDEX

Explanations

specific actions or events occurring sequentially

oai_token-act-pair · gpt-3.5-turbo

phrases associated with errors, failures, or issues

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

estine

-0.68

".[

-0.68

 objective

-0.66

sylv

-0.66

Therefore

-0.66

 independ

-0.65

 comprehens

-0.64

 advoc

-0.63

FORMATION

-0.63

 whilst

-0.62

POSITIVE LOGITS

utterstock

0.87

 Shutterstock

0.83

 Costco

0.72

 Clarks

0.67

 Courtesy

0.66

 driveway

0.65

 Pric

0.65

 FedEx

0.65

 pricey

0.64

 fries

0.62

Activations Density 1.993%

specific actions or events occurring sequentially

phrases associated with errors, failures, or issues

No Comments

No Known Activations