INDEX

Explanations

instances where someone is described as fearless or unafraid

oai_token-act-pair · gpt-3.5-turbo

phrases indicating fear or hesitation

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

soDeliveryDate

-1.06

sonian

-0.78

grounds

-0.71

valued

-0.69

icipated

-0.67

vice

-0.66

 reperto

-0.66

anooga

-0.65

DragonMagazine

-0.64

ollah

-0.63

POSITIVE LOGITS

wered

1.06

 speak

0.98

 deceive

0.97

 breathe

0.94

 capitalize

0.92

 criticize

0.92

 undertake

0.91

 defy

0.91

be

0.91

 survive

0.90

Activations Density 0.204%

instances where someone is described as fearless or unafraid

phrases indicating fear or hesitation

No Comments

No Known Activations