INDEX

Explanations

locations within cities

oai_token-act-pair · gpt-3.5-turbo

locations and street names within urban environments

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

merga

-0.95

ername

-0.72

Ü

-0.72

 herd

-0.72

 worms

-0.71

 Logged

-0.70

 inoc

-0.69

 sails

-0.69

 inval

-0.68

 herds

-0.68

POSITIVE LOGITS

 downtown

1.50

 Chinatown

1.44

 Manhattan

1.37

 Downtown

1.36

 Brooklyn

1.24

 Seattle

1.23

 Oakland

1.21

 Minneapolis

1.20

 Chicago

1.17

 Baltimore

1.16

Activations Density 0.176%

locations within cities

locations and street names within urban environments

No Comments

No Known Activations