INDEX

Explanations

expressions of excitement or happiness

oai_token-act-pair · gpt-3.5-turbo

expressions of excitement or strong positive emotions

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

ciplinary

-0.85

poral

-0.81

enhagen

-0.78

road

-0.78

lay

-0.73

icrobial

-0.72

dule

-0.70

sterdam

-0.68

prison

-0.67

icipated

-0.67

POSITIVE LOGITS

 exclaim

0.72

ION

0.69

 exclaimed

0.67

VID

0.66

 delight

0.65

iously

0.64

 delighted

0.64

 Euros

0.64

 Romeo

0.64

ÃįÃį

0.64

Activations Density 0.049%

expressions of excitement or happiness

expressions of excitement or strong positive emotions

No Comments

No Known Activations