INDEX

Explanations

references to outdoor spaces, specifically focusing on the concept of a yard

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "yard."

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

 Addiction

-0.72

 Fusion

-0.70

Insert

-0.70

iq

-0.66

Duo

-0.65

ogen

-0.64

ogens

-0.63

achi

-0.63

 Conan

-0.62

ami

-0.61

POSITIVE LOGITS

 yard

4.03

yard

2.55

 yards

2.49

yards

2.29

 Yard

2.23

 Yards

1.96

 backyard

1.47

 lawn

1.40

 porch

1.31

 garden

1.24

Activations Density 0.010%

references to outdoor spaces, specifically focusing on the concept of a yard

mentions of the term "yard."

No Comments

No Known Activations