INDEX

Explanations

phrases related to statistical margins of error

oai_token-act-pair · gpt-3.5-turbo

numerical data regarding error margins and statistical values

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

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

 Aires

-0.67

NetMessage

-0.65

 Activities

-0.65

hower

-0.64

 Engineers

-0.64

Apps

-0.63

chemical

-0.63

Mech

-0.63

 Journalism

-0.62

 Cooking

-0.62

POSITIVE LOGITS

 minus

1.09

 zero

1.04

 infinity

1.03

 inverse

0.95

 indifferent

0.95

equal

0.91

>=

0.91

 undefined

0.91

 neutral

0.90

nil

0.90

Activations Density 0.345%

phrases related to statistical margins of error

numerical data regarding error margins and statistical values

No Comments

No Known Activations