INDEX

Explanations

phrases related to packaging and product labeling

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "packaging" or "packs."

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

bered

-0.74

Downloadha

-0.68

 Cald

-0.68

abama

-0.65

Bie

-0.64

nesota

-0.63

 Pradesh

-0.63

sembly

-0.62

 Baldwin

-0.62

 compr

-0.61

POSITIVE LOGITS

aging

1.46

ages

1.36

agers

1.27

aged

1.26

erness

1.10

ager

1.09

ets

0.98

pack

0.98

AGES

0.98

er

0.92

Activations Density 0.023%

phrases related to packaging and product labeling

references to the concept of "packaging" or "packs."

No Comments

No Known Activations