INDEX

Explanations

phrases related to procedures, instructions, or guidelines

oai_token-act-pair · gpt-3.5-turbo

references to items or concepts presented in a list format

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Cho

-0.77

ledge

-0.68

eat

-0.67

gall

-0.66

jee

-0.66

venants

-0.65

Options

-0.65

agree

-0.65

agy

-0.64

biz

-0.64

POSITIVE LOGITS

 sake

1.88

 purposes

1.63

 purpose

1.48

 foreseeable

1.40

 duration

1.19

 upcoming

1.13

 remainder

1.11

ummies

1.06

 entirety

0.97

 benefit

0.95

Activations Density 0.152%

phrases related to procedures, instructions, or guidelines

references to items or concepts presented in a list format

No Comments

No Known Activations