INDEX

Explanations

words related to geography or location

oai_token-act-pair · gpt-3.5-turbo

terms related to geography and geographic concepts

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

alin

-1.03

lain

-0.90

nos

-0.89

eat

-0.85

rin

-0.85

ilts

-0.80

Case

-0.78

child

-0.75

ride

-0.75

ion

-0.74

POSITIVE LOGITS

 geographically

1.09

 geographic

0.95

 geographical

0.93

 illiter

0.93

 geography

0.89

 locations

0.83

 unemploy

0.83

 footprint

0.81

 location

0.80

 proximity

0.79

Activations Density 0.008%

words related to geography or location

terms related to geography and geographic concepts

No Comments

No Known Activations