INDEX

Explanations

questions ending with a question mark

oai_token-act-pair · gpt-3.5-turbo

question marks indicating inquiries or questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

nery

-0.83

 McMaster

-0.77

McA

-0.72

 McConnell

-0.70

leground

-0.67

 willing

-0.66

 Brock

-0.63

 resigned

-0.63

 overt

-0.63

 eroded

-0.62

POSITIVE LOGITS

Answer

1.20

ccording

1.04

Well

0.97

?????-?????-

0.95

RH

0.92

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.89

Brow

0.87

ÂłÂłÂłÂł

0.86

GU

0.86

Unit

0.86

Activations Density 0.128%

questions ending with a question mark

question marks indicating inquiries or questions

No Comments

No Known Activations