INDEX

Explanations

words related to specific urban locations, particularly referencing shopping centers, parks, and public squares

oai_token-act-pair · gpt-3.5-turbo

references to specific locations and squares within a community

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

ulin

-0.79

atical

-0.74

etically

-0.72

source

-0.70

emic

-0.69

Ò

-0.68

forces

-0.68

 inoc

-0.68

vae

-0.67

etimes

-0.67

POSITIVE LOGITS

 Plaza

1.53

 plaza

1.44

 Hotel

1.41

 Parking

1.35

 redevelopment

1.31

 Corridor

1.30

 apartments

1.30

 Neighborhood

1.28

 Shopping

1.27

 Boulevard

1.26

Activations Density 0.182%

words related to specific urban locations, particularly referencing shopping centers, parks, and public squares

references to specific locations and squares within a community

No Comments

No Known Activations