INDEX

Explanations

specific symbols and characters

oai_token-act-pair · gpt-3.5-turbo

special characters or formatting indicators

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

 Belg

-0.67

 board

-0.65

 wink

-0.65

 whichever

-0.64

 mate

-0.64

 scattering

-0.64

 leading

-0.64

 cheaply

-0.62

 casting

-0.62

Sic

-0.62

POSITIVE LOGITS

º

1.54

¹

1.48

»

1.42

Į

1.41

į

1.36

ª

1.35

®

1.34

£

1.32

Ń

1.26

«

1.23

Activations Density 0.138%

specific symbols and characters

special characters or formatting indicators

No Comments

No Known Activations