INDEX

Explanations

programming-related terms, particularly related to code execution and configuration

oai_token-act-pair · gpt-3.5-turbo

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

AIDS

-0.82

 Oprah

-0.73

assault

-0.71

Alabama

-0.70

America

-0.69

ampunk

-0.69

Americ

-0.67

African

-0.66

 America

-0.66

arians

-0.66

POSITIVE LOGITS

 bunch

1.06

 static

1.02

 subset

1.01

 comma

1.00

 separate

0.99

 single

0.98

few

0.98

 recursive

0.97

 dummy

0.97

 simple

0.96

Activations Density 0.190%

programming-related terms, particularly related to code execution and configuration

No Comments

No Known Activations