INDEX

Explanations

names of people and places, along with some related sentences

oai_token-act-pair · gpt-3.5-turbo

references to people and their relationships or status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Beacon

-0.87

 Monroe

-0.87

 Wilmington

-0.81

 Becky

-0.79

 Tacoma

-0.78

Myr

-0.77

 Spokane

-0.76

 Abby

-0.76

 Hydra

-0.76

 Syracuse

-0.75

POSITIVE LOGITS

 Singh

1.49

 Sharma

1.44

 Kumar

1.42

 Pradesh

1.38

jriwal

1.35

 Gujarat

1.32

 Punjab

1.32

umbai

1.31

 Maharashtra

1.31

 Bhar

1.28

Activations Density 1.769%

names of people and places, along with some related sentences

references to people and their relationships or status

No Comments

No Known Activations