INDEX

Explanations

phrases indicating someone's current or past association with a specific entity or group

oai_token-act-pair · gpt-3.5-turbo

instances of the word "with."

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

mart

-0.67

 reviews

-0.62

Armor

-0.60

 quiz

-0.59

 mislead

-0.59

 favorably

-0.59

ormon

-0.57

sylvania

-0.57

ä¸ī

-0.56

 reprint

-0.56

POSITIVE LOGITS

stood

1.37

 impunity

1.12

drawn

1.05

standing

1.03

draw

0.99

holding

0.94

 dignity

0.89

 regard

0.86

 utmost

0.84

 regards

0.83

Activations Density 0.122%

phrases indicating someone's current or past association with a specific entity or group

instances of the word "with."

No Comments

No Known Activations