INDEX

Explanations

references to licensing or licenses

oai_token-act-pair · gpt-3.5-turbo

words related to licensing or permissions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Ended

-0.71

 Unch

-0.68

 Admir

-0.67

ħĭ

-0.62

 Everywhere

-0.61

Yad

-0.59

 Lans

-0.58

adm

-0.58

Seb

-0.57

commit

-0.57

POSITIVE LOGITS

hess

1.37

ensing

1.34

enses

1.21

entious

1.19

enced

1.05

ious

0.95

ensable

0.95

atable

0.92

her

0.91

hes

0.90

Activations Density 0.047%

references to licensing or licenses

words related to licensing or permissions

No Comments

No Known Activations