INDEX

Explanations

mentions of the word "Ord" or variations like "Ordinator" and "Ordinance"

oai_token-act-pair · gpt-3.5-turbo

references to ordination and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Libre

-0.69

=-=-=-=-

-0.68

STEM

-0.68

Improve

-0.67

 Blacks

-0.67

itaire

-0.66

Wa

-0.65

Madison

-0.65

icago

-0.64

ï¸ı

-0.64

POSITIVE LOGITS

nance

1.55

inarily

1.42

inances

1.20

inary

1.19

inal

1.10

inance

1.06

inent

0.99

inated

0.97

eals

0.97

ination

0.96

Activations Density 0.007%

mentions of the word "Ord" or variations like "Ordinator" and "Ordinance"

references to ordination and related terminology

No Comments

No Known Activations