INDEX

Explanations

descriptions of violent altercations or assaults involving multiple individuals

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the" in various contexts

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

Not in Any Lists

No Comments

Negative Logits

osphere

-0.80

Ô

-0.78

abase

-0.78

Wik

-0.77

ushima

-0.77

obyl

-0.77

TPP

-0.76

erella

-0.76

æĹ

-0.76

FactoryReloaded

-0.75

POSITIVE LOGITS

 attacker

1.40

 assailant

1.35

 victim

1.27

 intruder

1.24

 assailants

1.22

 gunman

1.21

 occupants

1.21

 attackers

1.19

 perpetrator

1.19

 defendant

1.18

Activations Density 0.321%

descriptions of violent altercations or assaults involving multiple individuals

occurrences of the word "the" in various contexts

No Comments

No Known Activations