INDEX

Explanations

mentions of locations or areas

oai_token-act-pair · gpt-3.5-turbo

references to specific geographic locations and their related contexts

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

CVE

-0.85

BIL

-0.70

trak

-0.65

uning

-0.65

obe

-0.64

fully

-0.63

LY

-0.60

AMI

-0.60

ful

-0.59

uala

-0.59

POSITIVE LOGITS

 globe

1.02

 country

0.95

Atlantic

0.88

 aisle

0.87

 nation

0.84

 continent

0.84

 plains

0.82

 rainbow

0.82

 entire

0.82

 board

0.82

Activations Density 0.067%

mentions of locations or areas

references to specific geographic locations and their related contexts

No Comments

No Known Activations