INDEX

Explanations

first-person pronouns and phrases related to personal experiences and beliefs

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Consortium

-0.74

Gad

-0.64

 Rubio

-0.60

tnc

-0.59

earch

-0.59

ileaks

-0.58

lihood

-0.58

ses

-0.57

 Millennium

-0.57

 Mund

-0.57

POSITIVE LOGITS

'm

1.39

've

1.26

'll

1.13

'd

1.00

am

0.94

 intend

0.92

owe

0.91

ronic

0.89

 hope

0.89

 suppose

0.89

Activations Density 0.379%

first-person pronouns and phrases related to personal experiences and beliefs

No Comments

No Known Activations