INDEX

Explanations

noun phrases related to software functions or properties

oai_token-act-pair · gpt-3.5-turbo

phrases indicating possession or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

eem

-0.72

 prosecuting

-0.69

cus

-0.68

ensing

-0.64

oit

-0.62

catentry

-0.61

icking

-0.60

PHOTOS

-0.60

—-

-0.59

dding

-0.59

POSITIVE LOGITS

 been

1.36

 undergone

1.22

been

1.08

 Been

1.02

kell

0.96

stood

0.89

 gotten

0.88

 arisen

0.88

 grown

0.88

hed

0.87

Activations Density 0.412%

noun phrases related to software functions or properties

phrases indicating possession or characteristics

No Comments

No Known Activations