INDEX

Explanations

phrases related to inability or reluctance to do something

oai_token-act-pair · gpt-3.5-turbo

terms indicating inability or unwillingness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

soType

-0.90

values

-0.72

oop

-0.70

ramid

-0.70

anmar

-0.69

inventoryQuantity

-0.69

ership

-0.68

aza

-0.68

illance

-0.67

ebus

-0.66

POSITIVE LOGITS

 incapable

0.94

 compe

0.78

 wasting

0.76

 unwilling

0.71

 fools

0.71

 unable

0.67

bog

0.66

 unfit

0.66

 wastes

0.66

 insol

0.65

Activations Density 0.009%

phrases related to inability or reluctance to do something

terms indicating inability or unwillingness

No Comments

No Known Activations