INDEX

Explanations

phrases related to the video game character "Duke Nukem"

oai_token-act-pair · gpt-3.5-turbo

repeated references to the term "Duke."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

heny

-0.68

earchers

-0.67

ifax

-0.64

ion

-0.64

ally

-0.63

clair

-0.62

 Dragonbound

-0.61

raq

-0.61

iscal

-0.60

odic

-0.60

POSITIVE LOGITS

vich

0.93

unin

0.81

warm

0.81

UGH

0.77

erk

0.75

essee

0.72

ernel

0.71

hiro

0.71

Maker

0.71

uke

0.70

Activations Density 0.014%

phrases related to the video game character "Duke Nukem"

repeated references to the term "Duke."

No Comments

No Known Activations