INDEX

Explanations

proper nouns and names of organizations and institutions

oai_token-act-pair · gpt-3.5-turbo

names of individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

someone

-0.88

outer

-0.79

ometimes

-0.78

ctrl

-0.75

ogie

-0.75

ueless

-0.74

rots

-0.74

etheless

-0.73

ccording

-0.72

dyl

-0.72

POSITIVE LOGITS

 Memorial

1.33

 Foundation

1.30

LLP

1.18

 Institute

1.18

 Associates

1.17

 University

1.17

 Parkway

1.14

 Center

1.10

 Museum

1.09

 Hospital

1.08

Activations Density 0.177%

proper nouns and names of organizations and institutions

names of individuals and organizations

No Comments

No Known Activations