INDEX

Explanations

phrases related to love and relationships

oai_token-act-pair · gpt-3.5-turbo

themes related to love and friendship

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

•layer 5 - love

No Comments

Negative Logits

ħĭ

-0.97

ICLE

-0.74

*/(

-0.72

ocument

-0.71

ozo

-0.69

ottest

-0.68

 dilig

-0.68

incial

-0.66

ierre

-0.66

 scrut

-0.65

POSITIVE LOGITS

 dearly

0.78

rix

0.77

 solitude

0.73

cel

0.70

enberg

0.69

 daddy

0.67

 earthly

0.66

stic

0.66

 companions

0.64

thood

0.64

Activations Density 0.192%

phrases related to love and relationships

themes related to love and friendship

No Comments

No Known Activations