INDEX

Explanations

mentions of military actions and movements

oai_token-act-pair · gpt-3.5-turbo

content related to military operations and conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Epstein

-0.91

 Dickens

-0.84

 Titanic

-0.83

 Consumer

-0.81

 Scalia

-0.81

geist

-0.81

Â¢

-0.78

 Satoshi

-0.78

Consumer

-0.77

dream

-0.76

POSITIVE LOGITS

 retake

1.32

 recapt

1.30

 siege

1.28

 besie

1.27

 artillery

1.25

 blockade

1.20

 reinforcements

1.19

 shelling

1.18

 skirm

1.17

 retreating

1.15

Activations Density 0.409%

mentions of military actions and movements

content related to military operations and conflict

No Comments

No Known Activations