INDEX

Explanations

references to computer chips

oai_token-act-pair · gpt-3.5-turbo

references to various types of chips in technology

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

æĢ

-0.70

 gearing

-0.68

Vaj

-0.66

 Territ

-0.66

 Canal

-0.65

 Scandinav

-0.64

 Refugee

-0.64

 Stranger

-0.62

 Parish

-0.61

 Dayton

-0.60

POSITIVE LOGITS

otle

1.66

mun

1.14

board

0.97

washer

0.90

chip

0.89

ambers

0.89

 implanted

0.89

Chip

0.81

 chip

0.81

maker

0.81

Activations Density 0.039%

references to computer chips

references to various types of chips in technology

No Comments

No Known Activations