INDEX

Explanations

phrases related to personal development and success

oai_token-act-pair · gpt-3.5-turbo

instances of the word "in" to highlight locations or contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

linger

-0.67

CLASSIFIED

-0.66

 lodged

-0.64

 Released

-0.62

Released

-0.60

username

-0.60

-0.59

 Sorceress

-0.58

Voice

-0.58

llor

-0.57

POSITIVE LOGITS

 spite

1.27

 lieu

1.24

 regards

1.23

 accordance

1.21

 vitro

1.19

animate

1.15

ordinate

1.15

 relation

1.15

 order

1.13

 terms

1.12

Activations Density 0.557%

phrases related to personal development and success

instances of the word "in" to highlight locations or contexts

No Comments

No Known Activations