INDEX

Explanations

phrases related to responsibilities or obligations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating obligation or responsibility

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

-0.72

ippi

-0.70

 rumored

-0.68

expected

-0.67

furt

-0.67

listed

-0.66

 trending

-0.63

 Fres

-0.62

 touted

-0.61

 uproar

-0.61

POSITIVE LOGITS

 undertake

1.08

 fulfill

1.07

 protect

1.02

 uphold

0.99

 abide

0.98

 fulfil

0.97

 perform

0.96

 participate

0.95

 safeguard

0.95

act

0.95

Activations Density 0.344%

phrases related to responsibilities or obligations

phrases indicating obligation or responsibility

No Comments

No Known Activations