INDEX

Explanations

expressions of gratitude and appreciation

oai_token-act-pair · gpt-3.5-turbo

expressions of gratitude or thanks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

umin

-0.79

ewitness

-0.77

apeshifter

-0.76

 quartz

-0.69

nai

-0.68

ihil

-0.66

 undet

-0.65

ulate

-0.64

agin

-0.64

ãĤ¼ãĤ¦ãĤ¹

-0.63

POSITIVE LOGITS

 Thank

0.96

:)

0.94

 âĿ

0.93

 Please

0.92

 Congratulations

0.90

 Merry

0.89

 ðŁĻĤ

0.88

:-)

0.87

We

0.84

 Hope

0.83

Activations Density 0.233%

expressions of gratitude and appreciation

expressions of gratitude or thanks

No Comments

No Known Activations