INDEX

Explanations

mentions of the word "Toy" appearing in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to toys and related products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aunder

-0.78

 circulation

-0.67

umbers

-0.67

idency

-0.67

ounty

-0.66

icter

-0.65

xual

-0.65

etheless

-0.64

aeda

-0.63

ournals

-0.63

POSITIVE LOGITS

Toy

1.11

Toy

1.00

 Toys

0.95

ota

0.95

 Crate

0.87

shop

0.80

neys

0.78

Box

0.78

 toys

0.77

ãĤ´

0.76

Activations Density 0.007%

mentions of the word "Toy" appearing in various contexts

references to toys and related products

No Comments

No Known Activations