INDEX

Explanations

references to vampires

oai_token-act-pair · gpt-3.5-turbo

references to vampires and related creatures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

•Vampire neurons

No Comments

Negative Logits

qual

-0.85

llah

-0.81

lems

-0.78

WER

-0.78

words

-0.77

daq

-0.76

)=(

-0.75

enegger

-0.75

eq

-0.75

equality

-0.74

POSITIVE LOGITS

 squid

1.22

 hunter

0.92

 vampires

0.90

 vampire

0.89

 Masquerade

0.84

 Dracula

0.80

 remnant

0.78

 Slayer

0.77

ampire

0.76

 Vampire

0.76

Activations Density 0.028%

references to vampires

references to vampires and related creatures

No Comments

No Known Activations