INDEX

Explanations

references to clothing and dressing-related actions or situations

oai_token-act-pair · gpt-3.5-turbo

references to clothing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

umar

-0.67

utherford

-0.67

ipolar

-0.66

 Woodward

-0.66

mary

-0.64

 probable

-0.64

 Kern

-0.63

Iraq

-0.63

odcast

-0.61

 Democr

-0.61

POSITIVE LOGITS

leeve

1.15

pins

1.06

 clothes

1.05

 clothing

1.01

 garments

1.00

 apparel

0.98

 worn

0.97

puter

0.97

bag

0.95

bags

0.94

Activations Density 0.009%

references to clothing and dressing-related actions or situations

references to clothing

No Comments

No Known Activations