INDEX

Explanations

the abbreviation "Mo" followed by a combination of letters and numbers

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the term "Mo" or its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Integrity

-0.72

 responsibility

-0.70

 Icelandic

-0.67

 Identification

-0.65

 Prohibition

-0.65

 Discrimination

-0.62

acters

-0.61

 Prelude

-0.61

 DRAGON

-0.61

Reloaded

-0.60

POSITIVE LOGITS

ose

1.09

oney

1.05

oby

0.99

osh

0.95

ogly

0.93

utes

0.92

oser

0.91

omon

0.91

uls

0.90

ogie

0.89

Activations Density 0.015%

the abbreviation "Mo" followed by a combination of letters and numbers

repeated mentions of the term "Mo" or its variations

No Comments

No Known Activations