INDEX

Explanations

expressions of gratitude or appreciation

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soDeliveryDate

-0.81

buster

-0.79

rooms

-0.77

infect

-0.76

iop

-0.70

prep

-0.69

fall

-0.69

 Tycoon

-0.67

shr

-0.66

cop

-0.66

POSITIVE LOGITS

 appreciation

0.85

 compliments

0.84

how

0.75

 appreciate

0.74

 contributions

0.73

¿½

0.72

reciation

0.71

ments

0.69

ĸļ

0.69

 advances

0.68

Activations Density 0.038%

expressions of gratitude or appreciation

No Comments

No Known Activations