INDEX

Explanations

references to carbon and carbon-related terms

oai_token-act-pair · gpt-3.5-turbo

instances of the word "carbon."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

GBT

-0.81

 Psychiatric

-0.80

udeb

-0.80

HCR

-0.80

DragonMagazine

-0.78

akings

-0.74

---------------

-0.74

ERY

-0.72

 Niet

-0.71

ERS

-0.71

POSITIVE LOGITS

 dioxide

1.65

 emissions

1.07

 fiber

1.00

 emission

0.99

 fibre

0.96

 footprint

0.96

ohydrate

0.95

 footprints

0.90

 gases

0.89

 offsets

0.88

Activations Density 0.022%

references to carbon and carbon-related terms

instances of the word "carbon."

No Comments

No Known Activations