INDEX

Explanations

terms related to rental agreements or housing costs

oai_token-act-pair · gpt-3.5-turbo

references to rental housing and related terms

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

umenthal

-0.75

ambers

-0.74

otine

-0.73

ctions

-0.73

OTUS

-0.71

 Flavoring

-0.70

ulkan

-0.70

doi

-0.69

 Chemistry

-0.69

alions

-0.67

POSITIVE LOGITS

 renters

1.03

 renting

1.03

 apartments

0.98

 landlords

0.93

 tenants

0.92

 affordability

0.91

 rent

0.90

 rented

0.89

 rentals

0.89

 rental

0.88

Activations Density 0.036%

terms related to rental agreements or housing costs

references to rental housing and related terms

No Comments

No Known Activations