INDEX

Explanations

specific mentions of people and actions related to incidents or events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ç¥ŀ

-0.77

joice

-0.73

 Gohan

-0.71

luster

-0.70

ccoli

-0.69

Enjoy

-0.68

 Buddhism

-0.67

 Krugman

-0.67

topia

-0.67

 Luffy

-0.67

POSITIVE LOGITS

 latter

1.20

 same

1.15

 heaviest

1.00

FBI

0.99

 defendant

0.99

 complainant

0.98

 alleged

0.97

 aforementioned

0.97

 incident

0.96

 affidavit

0.95

Activations Density 1.348%

specific mentions of people and actions related to incidents or events

occurrences of the word "the."

No Comments

No Known Activations