INDEX

Explanations

phrases indicating permission or freedom to act

oai_token-act-pair · gpt-3.5-turbo

phrases expressing permission or freedom to take certain actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

quickShipAvailable

-0.81

soDeliveryDate

-0.73

need

-0.72

bush

-0.71

ritical

-0.67

grain

-0.66

 specificity

-0.65

requires

-0.64

warming

-0.63

Ĳ

-0.63

POSITIVE LOGITS

 roam

1.15

 explore

1.12

 indulge

1.03

 pursue

1.03

 breathe

0.99

 choose

0.97

 participate

0.96

 speak

0.95

 negotiate

0.95

 enter

0.94

Activations Density 0.099%

phrases indicating permission or freedom to act

phrases expressing permission or freedom to take certain actions

No Comments

No Known Activations