INDEX

Explanations

mentions of tenants in real estate or property contexts

oai_token-act-pair · gpt-3.5-turbo

references to tenants and tenant-related issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

erald

-0.74

ardon

-0.73

aque

-0.73

nesia

-0.71

gio

-0.70

ombs

-0.70

vernment

-0.69

ebin

-0.69

 Flavoring

-0.69

 Pike

-0.69

POSITIVE LOGITS

 tenants

1.45

 tenant

1.35

 landlords

0.94

 renters

0.90

 leases

0.88

 tenancy

0.87

ele

0.83

 occupancy

0.81

iffs

0.80

 landlord

0.78

Activations Density 0.005%

mentions of tenants in real estate or property contexts

references to tenants and tenant-related issues

No Comments

No Known Activations