INDEX

Explanations

locations or geographical terms

oai_token-act-pair · gpt-3.5-turbo

terms related to location sharing and mapping technologies

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

nikov

-0.83

ishi

-0.83

EStreamFrame

-0.82

esson

-0.81

iesel

-0.80

 Weinstein

-0.79

 Faust

-0.78

aughter

-0.76

luaj

-0.75

laugh

-0.75

POSITIVE LOGITS

 maps

2.28

 Maps

2.16

map

2.13

Map

1.97

Maps

1.93

 mapping

1.83

maps

1.82

Map

1.73

 mapped

1.69

 geography

1.59

Activations Density 0.493%

locations or geographical terms

terms related to location sharing and mapping technologies

No Comments

No Known Activations