INDEX

Explanations

verbs related to doors and physical actions or states concerning doors

oai_token-act-pair · gpt-3.5-turbo

references to doors and their functionalities

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

lihood

-0.80

irtual

-0.77

igenous

-0.74

azeera

-0.71

yss

-0.67

erate

-0.67

ovych

-0.66

erent

-0.66

ollah

-0.66

ousand

-0.66

POSITIVE LOGITS

bell

1.25

door

1.21

 doors

1.08

doors

1.07

steps

1.05

holes

1.04

frame

0.95

 door

0.95

ways

0.93

plates

0.93

Activations Density 0.024%

verbs related to doors and physical actions or states concerning doors

references to doors and their functionalities

No Comments

No Known Activations