INDEX

Explanations

phrases related to data science and technology

oai_token-act-pair · gpt-3.5-turbo

occurrences of scientific or technical terms related to data or metrics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•GPT2 L10 resid: 'LRRRRRLLRRRL'[:-3]

No Comments

Negative Logits

idth

-0.81

 Bleach

-0.78

 Chevron

-0.73

 Cherokee

-0.68

 Bowen

-0.68

 Sieg

-0.66

 crow

-0.64

 Dawkins

-0.63

 Cruz

-0.63

Qin

-0.63

POSITIVE LOGITS

1.37

1.35

MM

1.32

MF

1.25

MN

1.23

mt

1.23

MX

1.21

ms

1.20

MT

1.20

MW

1.20

Activations Density 0.771%

phrases related to data science and technology

occurrences of scientific or technical terms related to data or metrics

No Comments

No Known Activations