INDEX

Explanations

mentions of rent and housing-related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of "rent" and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

doi

-0.79

ctions

-0.75

 Flavoring

-0.73

olean

-0.70

olics

-0.70

aque

-0.68

 Chemistry

-0.66

alse

-0.66

ebin

-0.65

================================================================

-0.65

POSITIVE LOGITS

 rent

0.92

 rented

0.85

 renters

0.84

 apartments

0.84

 renting

0.84

 cheaply

0.80

 Rent

0.75

Chart

0.75

 housing

0.73

 Estate

0.72

Activations Density 0.013%

mentions of rent and housing-related terms

mentions of "rent" and related concepts

No Comments

No Known Activations