INDEX

Explanations

specific phrases related to passages in a text that appear to be of importance or significance

oai_token-act-pair · gpt-3.5-turbo

references to statements and arguments made within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anmar

-0.70

 Skydragon

-0.68

isoft

-0.67

 ILCS

-0.65

 Settlement

-0.63

senal

-0.63

ahime

-0.63

Choose

-0.62

profit

-0.62

 Registration

-0.62

POSITIVE LOGITS

 begs

1.47

 sums

1.41

 rings

1.39

 echoes

1.32

 sounds

1.31

 ignores

1.29

 sounded

1.27

 implies

1.27

 bothers

1.26

 applies

1.26

Activations Density 0.246%

specific phrases related to passages in a text that appear to be of importance or significance

references to statements and arguments made within the text

No Comments

No Known Activations