INDEX

Explanations

commands or instructions

oai_token-act-pair · gpt-3.5-turbo

commands or directives given to individuals

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

 Appears

-0.92

 Ended

-0.66

quickShipAvailable

-0.66

majority

-0.66

CLR

-0.64

 threaded

-0.63

 proven

-0.62

bour

-0.62

 indexed

-0.61

bara

-0.61

POSITIVE LOGITS

 beware

1.00

 evacuate

0.98

 obey

0.97

 behave

0.95

 abandon

0.93

 bury

0.92

 shove

0.92

 avoid

0.92

 keep

0.92

 prioritize

0.91

Activations Density 0.107%

commands or instructions

commands or directives given to individuals

No Comments

No Known Activations