INDEX

Explanations

references to shipping and related terms within text

oai_token-act-pair · gpt-3.5-turbo

references to shipping logistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

si

-0.80

atives

-0.76

nered

-0.76

ivas

-0.73

 Glas

-0.72

ellen

-0.71

jac

-0.69

lder

-0.68

opes

-0.66

sson

-0.66

POSITIVE LOGITS

 containers

0.95

 shipping

0.88

 Shipping

0.87

wreck

0.79

 container

0.78

 Yamato

0.75

 SEAL

0.73

 receipts

0.73

mith

0.71

Ship

0.71

Activations Density 0.023%

references to shipping and related terms within text

references to shipping logistics

No Comments

No Known Activations