INDEX

Explanations

phrases related to organizations and leadership positions

oai_token-act-pair · gpt-3.5-turbo

mentions of organizational leadership positions and affiliations

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

grain

-0.84

Ocean

-0.76

Oracle

-0.75

Luck

-0.72

Bench

-0.72

olphin

-0.71

 Colts

-0.71

 Hitman

-0.70

isher

-0.68

Samsung

-0.67

POSITIVE LOGITS

 membership

1.64

 disband

1.50

 disbanded

1.45

 Membership

1.43

 affiliation

1.36

 adherents

1.32

 members

1.31

Members

1.30

 dues

1.30

 organizing

1.27

Activations Density 0.624%

phrases related to organizations and leadership positions

mentions of organizational leadership positions and affiliations

No Comments

No Known Activations