INDEX

Explanations

political and economic terms related to policy and ideology, particularly focusing on social structures and reform

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

concepts related to political ideologies and social structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

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

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_post

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

 Crusher

-0.69

 Famous

-0.69

 Frie

-0.66

pects

-0.66

handle

-0.63

 Died

-0.63

 Writer

-0.62

 Words

-0.61

 Engine

-0.61

 Faces

-0.61

POSITIVE LOGITS

 emancipation

1.13

conserv

1.13

ism

1.12

 socialism

1.12

 hegemony

1.09

 domination

1.05

 capitalism

1.02

 autonomy

1.01

 democracy

0.99

 integration

0.99

Activations Density 0.356%

political and economic terms related to policy and ideology, particularly focusing on social structures and reform

concepts related to political ideologies and social structures

No Comments

No Known Activations