INDEX

Explanations

code snippets and technical terms related to programming

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

 Lung

-0.74

 Protective

-0.71

 Relationship

-0.67

 Bulls

-0.67

 Weeks

-0.66

 Arms

-0.66

 Opportunity

-0.63

 Influence

-0.63

 Tanks

-0.63

Orderable

-0.63

POSITIVE LOGITS

gmail

1.16

yahoo

1.13

atl

1.04

sd

1.02

nl

0.94

bg

0.93

gui

0.92

blogspot

0.91

wordpress

0.88

live

0.86

Activations Density 0.244%

code snippets and technical terms related to programming

No Comments

No Known Activations