INDEX

Explanations

phrases related to deserving or earning something

oai_token-act-pair · gpt-3.5-turbo

expressions about desires and expectations related to fairness or entitlements

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

arnaev

-0.87

iannopoulos

-0.77

USS

-0.72

ecycle

-0.69

cephal

-0.68

ashtra

-0.67

 craw

-0.66

 seism

-0.66

arij

-0.64

 Cycle

-0.64

POSITIVE LOGITS

ļéĨĴ

1.08

 unconditional

1.08

 necessities

1.05

 concessions

1.03

 sacrific

1.00

 ransom

0.99

 goodies

0.97

 gifts

0.96

 priceless

0.96

 reimbursement

0.96

Activations Density 0.626%

phrases related to deserving or earning something

expressions about desires and expectations related to fairness or entitlements

No Comments

No Known Activations