INDEX

Explanations

words related to physical sciences, such as gases, ions, radiation, and particles

oai_token-act-pair · gpt-3.5-turbo

concepts related to scientific processes and physical interactions between particles and gases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Franch

-0.78

 Homeless

-0.73

 advoc

-0.70

 couch

-0.68

 Bust

-0.68

ooter

-0.65

 regulars

-0.64

soDeliveryDate

-0.64

 Manor

-0.64

pkg

-0.63

POSITIVE LOGITS

 electrons

1.30

 photons

1.20

 molecules

1.19

 molecule

1.17

 photon

1.14

 molecular

1.12

 nucle

1.11

 graphene

1.08

 atoms

1.08

 particles

1.08

Activations Density 1.260%

words related to physical sciences, such as gases, ions, radiation, and particles

concepts related to scientific processes and physical interactions between particles and gases

No Comments

No Known Activations