INDEX

Explanations

words related to politics and politicians

oai_token-act-pair · gpt-3.5-turbo

mentions of political entities or terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

RED

-0.71

uran

-0.70

 pity

-0.70

urous

-0.69

 Carbuncle

-0.68

uring

-0.67

 Moor

-0.67

lamm

-0.67

MQ

-0.66

URN

-0.66

POSITIVE LOGITS

icians

1.17

ifact

1.10

ician

1.03

icial

0.96

ically

0.94

 Polit

0.89

eness

0.86

 correctness

0.83

ique

0.78

 Pengu

0.77

Activations Density 0.009%

words related to politics and politicians

mentions of political entities or terms

No Comments

No Known Activations