INDEX

Explanations

geographical locations

oai_token-act-pair · gpt-3.5-turbo

specific technical terms and jargon associated with biology and data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Happ

-0.63

Khe

-0.63

 Pirate

-0.63

 Pall

-0.59

rish

-0.59

DragonMagazine

-0.58

 Sheet

-0.56

arget

-0.55

mouth

-0.55

bole

-0.54

POSITIVE LOGITS

anchester

0.82

acia

0.75

å£«

0.72

apache

0.66

psons

0.66

ĸ

0.65

Ô

0.65

agues

0.62

emort

0.62

inatory

0.61

Activations Density 0.203%

geographical locations

specific technical terms and jargon associated with biology and data analysis

No Comments

No Known Activations