INDEX

Explanations

phrases related to economic and political structures, including capitalism, oligarchy, and profiting aspects like economics or politics

oai_token-act-pair · gpt-3.5-turbo

terms related to economic exploitation and capitalism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Advent

-0.80

ãĥ¼ãĥ³

-0.74

netflix

-0.73

 Metatron

-0.73

 Inquisition

-0.69

Hug

-0.69

 Cait

-0.66

 Ridley

-0.65

leigh

-0.64

 Ribbon

-0.64

POSITIVE LOGITS

paying

1.11

 profits

1.10

 scams

1.09

 profit

1.06

 dealings

1.03

 laundering

1.02

 bribe

1.02

 bribes

0.97

 banker

0.96

 financed

0.96

Activations Density 0.182%

phrases related to economic and political structures, including capitalism, oligarchy, and profiting aspects like economics or politics

terms related to economic exploitation and capitalism

No Comments

No Known Activations