INDEX

Explanations

locations described by their distance from another place

oai_token-act-pair · gpt-3.5-turbo

distances in miles and kilometers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

eer

-0.69

illions

-0.69

isner

-0.68

 Encyclopedia

-0.66

geist

-0.65

alien

-0.61

eers

-0.61

oly

-0.57

udeb

-0.57

found

-0.56

POSITIVE LOGITS

 southeast

1.32

 southwest

1.31

 northwest

1.28

 northeast

1.27

 south

1.19

 inland

1.18

 east

1.16

 west

1.12

 north

1.10

 away

1.08

Activations Density 0.042%

locations described by their distance from another place

distances in miles and kilometers

No Comments

No Known Activations