INDEX

Explanations

words related to jewelry and accessories

oai_token-act-pair · gpt-3.5-turbo

references to jewelry and related items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Poverty

-0.71

 Chattanooga

-0.70

SPA

-0.70

ãĥ´

-0.70

zee

-0.69

bern

-0.67

ABE

-0.67

anqu

-0.66

ãĥ¯ãĥ³

-0.66

 Wolves

-0.66

POSITIVE LOGITS

ellery

1.33

 jewelry

1.21

 bracelet

1.15

 necklace

1.11

jew

1.03

jew

1.01

 jewels

0.93

 jewel

0.92

rings

0.90

 wire

0.87

Activations Density 0.029%

words related to jewelry and accessories

references to jewelry and related items

No Comments

No Known Activations