INDEX

Explanations

mentions of military or law enforcement activities involving the keyword "Troops"

oai_token-act-pair · gpt-3.5-turbo

references to a specific team or entity, indicated by the term "Tro."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

UAL

-0.71

ually

-0.71

 Reloaded

-0.62

arians

-0.59

NOW

-0.59

eers

-0.58

ual

-0.58

++++++++++++++++

-0.57

iewicz

-0.57

ModLoader

-0.56

POSITIVE LOGITS

dden

1.27

opers

1.15

ppo

1.08

phies

1.07

pez

1.04

tsky

1.03

plets

1.02

phy

0.99

oping

0.99

tted

0.98

Activations Density 0.040%

mentions of military or law enforcement activities involving the keyword "Troops"

references to a specific team or entity, indicated by the term "Tro."

No Known Activations