INDEX

Explanations

words related to emotional states of happiness

oai_token-act-pair · gpt-3.5-turbo

expressions of happiness

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 - happiness

No Comments

Negative Logits

ngth

-0.80

soDeliveryDate

-0.79

DoS

-0.77

ciplinary

-0.76

BOOK

-0.72

Downloadha

-0.71

çīĪ

-0.70

authorized

-0.70

OLOGY

-0.69

zan

-0.68

POSITIVE LOGITS

joy

0.86

vale

0.84

istic

0.74

 Meal

0.71

 âĶľ

0.70

 happily

0.70

 birthday

0.70

 happy

0.68

 endings

0.65

 Onion

0.65

Activations Density 0.022%

words related to emotional states of happiness

expressions of happiness

No Comments

No Known Activations