INDEX

Explanations

references to royalty or monarchy, particularly focusing on Queen-related terms

oai_token-act-pair · gpt-3.5-turbo

references to the Queen, specifically in relation to her name and titles

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

sych

-0.73

kson

-0.70

letcher

-0.69

herer

-0.69

odcast

-0.67

ramid

-0.67

razil

-0.64

aneous

-0.63

 unaff

-0.63

 Extend

-0.63

POSITIVE LOGITS

 Anne

1.09

pin

0.92

 Elizabeth

0.88

 Mother

0.87

stown

0.86

 Mary

0.83

Queen

0.83

 Victoria

0.81

Bee

0.79

pins

0.79

Activations Density 0.019%

references to royalty or monarchy, particularly focusing on Queen-related terms

references to the Queen, specifically in relation to her name and titles

No Comments

No Known Activations