INDEX

Explanations

quotations

oai_token-act-pair · gpt-3.5-turbo

quotation marks and direct speech

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 challeng

-0.65

 adjud

-0.62

 prelim

-0.60

 administr

-0.59

 phon

-0.59

va

-0.56

 outsourcing

-0.56

 grammar

-0.56

 footing

-0.55

 dyed

-0.55

POSITIVE LOGITS

We

0.90

BuyableInstoreAndOnline

0.88

 largeDownload

0.81

Justice

0.81

Our

0.80

Operation

0.77

Sorry

0.77

Vers

0.76

Shut

0.76

Activations Density 0.103%

quotations

quotation marks and direct speech

No Comments

No Known Activations