INDEX

Explanations

cities and locations where events or meetings have taken place

oai_token-act-pair · gpt-3.5-turbo

locations of notable meetings and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Finder

-0.70

utenberg

-0.67

gotten

-0.66

 trooper

-0.65

 regulars

-0.63

 caller

-0.62

gage

-0.61

 regress

-0.60

 seasons

-0.60

 Rebell

-0.60

POSITIVE LOGITS

 Hilton

0.95

 Marriott

0.83

 Hotel

0.76

 honoring

0.75

ONDON

0.75

 Exhibition

0.73

Teg

0.72

 Theatre

0.72

 Pavilion

0.72

 Dhabi

0.71

Activations Density 0.365%

cities and locations where events or meetings have taken place

locations of notable meetings and events

No Comments

No Known Activations