INDEX

Explanations

expressions related to being alone

oai_token-act-pair · gpt-3.5-turbo

phrases relating to feelings of loneliness

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

aptic

-0.78

ickr

-0.77

nant

-0.76

pse

-0.72

EMP

-0.72

ummies

-0.69

andum

-0.69

 Briggs

-0.68

enegger

-0.67

ounces

-0.67

POSITIVE LOGITS

 unaccompanied

0.72

 alone

0.72

 confinement

0.70

 Alone

0.68

alone

0.68

icated

0.66

åŃĲ

0.65

hall

0.64

stretched

0.64

lihood

0.63

Activations Density 0.015%

expressions related to being alone

phrases relating to feelings of loneliness

No Comments

No Known Activations