INDEX

Explanations

keywords related to emotional well-being and positive feelings

oai_token-act-pair · gpt-3.5-turbo

concepts related to happiness and well-being

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

sonian

-0.81

MpServer

-0.77

enegger

-0.71

soDeliveryDate

-0.70

DoS

-0.70

 Cosponsors

-0.70

heny

-0.69

CFR

-0.67

 Runner

-0.65

 Shinra

-0.64

POSITIVE LOGITS

fulness

0.84

ful

0.82

idays

0.79

 happiness

0.78

 expectancy

0.77

appiness

0.75

ternity

0.74

aviour

0.73

 wellbeing

0.73

istic

0.72

Activations Density 0.019%

keywords related to emotional well-being and positive feelings

concepts related to happiness and well-being

No Comments

No Known Activations