INDEX

Explanations

positions and roles in a political context, particularly related to a specific individual

oai_token-act-pair · gpt-3.5-turbo

references to political figures and their roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Instrument

-0.83

 Austral

-0.83

 glim

-0.79

 Marathon

-0.78

unicip

-0.77

EVA

-0.75

externalActionCode

-0.75

 Compos

-0.73

 Tasmania

-0.73

 liner

-0.71

POSITIVE LOGITS

 Bannon

2.17

 Breitbart

1.82

 Priebus

1.80

 Kushner

1.53

 Spicer

1.49

 Manafort

1.46

 Ivanka

1.41

andowski

1.38

 Trump

1.34

 Gork

1.34

Activations Density 0.184%

positions and roles in a political context, particularly related to a specific individual

references to political figures and their roles

No Comments

No Known Activations