INDEX

Explanations

phrases related to rankings or superlatives

oai_token-act-pair · gpt-3.5-turbo

phrases indicating notable events or rankings

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

EngineDebug

-0.81

ALSE

-0.73

Query

-0.70

mil

-0.68

uce

-0.63

roth

-0.63

ido

-0.62

DragonMagazine

-0.62

½

-0.61

POSITIVE LOGITS

efficiency

1.00

clusively

0.99

ordinate

0.91

 regards

0.90

animate

0.89

ducers

0.89

clusions

0.89

 vitro

0.88

 conjunction

0.87

 lieu

0.86

Activations Density 0.158%

phrases related to rankings or superlatives

phrases indicating notable events or rankings

No Comments

No Known Activations