INDEX

Explanations

words related to clothing and attire

oai_token-act-pair · gpt-3.5-turbo

references to clothing and attire

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

=-=-=-=-

-0.62

uliffe

-0.62

EStreamFrame

-0.62

edia

-0.62

à¼

-0.62

OUNT

-0.61

emort

-0.61

Translation

-0.60

ommod

-0.59

ISO

-0.59

POSITIVE LOGITS

 wear

1.29

 worn

1.27

wear

1.18

 Wear

1.13

 wore

1.08

 wears

1.01

 apparel

0.99

ables

0.98

bands

0.96

 wearer

0.96

Activations Density 0.009%

words related to clothing and attire

references to clothing and attire

No Comments

No Known Activations