INDEX

Explanations

words related to days of the week, specifically "Sunday"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Sunday."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ript

-0.93

arist

-0.83

ever

-0.79

keye

-0.78

laus

-0.78

eded

-0.77

ortment

-0.76

egal

-0.76

esthetic

-0.75

ebook

-0.74

POSITIVE LOGITS

 afternoon

1.33

 mornings

1.29

 morning

1.28

 evening

1.14

 nights

1.12

 night

1.11

 Sunday

1.09

 brunch

1.06

 Night

1.05

 Sabbath

0.98

Activations Density 0.016%

words related to days of the week, specifically "Sunday"

occurrences of the word "Sunday."

No Comments

No Known Activations