INDEX

Explanations

mentions of privileges or privileged status

oai_token-act-pair · gpt-3.5-turbo

references to privilege

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Harvest

-0.70

 Lighting

-0.67

glers

-0.65

 Alchemy

-0.64

 pickups

-0.63

atoon

-0.63

 Lash

-0.62

 Animated

-0.62

zyme

-0.62

NH

-0.62

POSITIVE LOGITS

 privileged

3.75

priv

2.62

 privilege

2.43

 privileges

2.36

 Priv

2.18

Priv

2.05

ileged

2.00

ilege

1.60

 priv

1.56

 advant

1.14

Activations Density 0.026%

mentions of privileges or privileged status

references to privilege

No Comments

No Known Activations