INDEX

Explanations

references to royalty or queens

oai_token-act-pair · gpt-3.5-turbo

mentions of royalty, specifically those related to queens

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

kson

-0.81

odcast

-0.71

razil

-0.69

iasco

-0.68

 Extend

-0.68

letcher

-0.66

aneous

-0.64

sych

-0.64

ramid

-0.64

aneers

-0.64

POSITIVE LOGITS

 Anne

1.10

pin

0.91

 Elizabeth

0.87

Queen

0.85

 Mary

0.83

 Victoria

0.82

 Mother

0.81

Bee

0.81

 Alexandra

0.80

flower

0.79

Activations Density 0.019%

references to royalty or queens

mentions of royalty, specifically those related to queens

No Comments

No Known Activations