INDEX

Explanations

locations or coordinates

oai_token-act-pair · gpt-3.5-turbo

references to location or spatial positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

maxwell

-0.78

 Chou

-0.78

 Perkins

-0.76

ovember

-0.72

 drip

-0.70

 Payne

-0.70

Kou

-0.70

bush

-0.68

 Achieve

-0.68

 overshadow

-0.66

POSITIVE LOGITS

loc

3.24

Loc

3.12

Loc

3.12

loc

2.84

LOC

1.93

LOC

1.59

 locale

1.41

oci

1.38

location

1.22

 Locke

1.15

Activations Density 0.046%

locations or coordinates

references to location or spatial positioning

No Comments

No Known Activations