INDEX

Explanations

words related to consciousness and awareness

oai_token-act-pair · gpt-3.5-turbo

references to consciousness and awareness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

idated

-0.76

 McGr

-0.67

arious

-0.65

qv

-0.64

headers

-0.63

ACA

-0.63

ADE

-0.63

adr

-0.62

INGTON

-0.61

xit

-0.61

POSITIVE LOGITS

 conscious

1.06

conscious

1.05

 consciousness

0.86

 Conscious

0.85

ness

0.84

washing

0.84

mind

0.84

edly

0.84

matter

0.83

awareness

0.81

Activations Density 0.019%

words related to consciousness and awareness

references to consciousness and awareness

No Comments

No Known Activations