INDEX

Explanations

phrases related to upgrading products or services

oai_token-act-pair · gpt-3.5-turbo

terms related to upgrading or enhancements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

pal

-0.75

bered

-0.74

 Caption

-0.70

avery

-0.69

fried

-0.67

 Unch

-0.66

zman

-0.65

otropic

-0.64

tering

-0.64

¬

-0.64

POSITIVE LOGITS

grades

1.02

grading

0.98

 upgrades

0.93

graded

0.92

ments

0.91

 upgrade

0.87

xual

0.80

 downgrade

0.80

mentation

0.79

 upgrading

0.74

Activations Density 0.025%

phrases related to upgrading products or services

terms related to upgrading or enhancements

No Comments

No Known Activations