INDEX

Explanations

mentions of political leaders, specifically Prime Ministers

oai_token-act-pair · gpt-3.5-turbo

references to political leaders, specifically prime ministers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

bleacher

-0.74

cox

-0.71

ioch

-0.68

uper

-0.68

entric

-0.68

SOURCE

-0.66

 Valhalla

-0.65

ASED

-0.64

 Apply

-0.64

ciplinary

-0.63

POSITIVE LOGITS

 Minister

1.19

 Ministers

1.11

 minister

1.08

 ministers

1.08

 ministerial

1.07

 Prime

0.90

 Directive

0.87

 Secretary

0.82

Prime

0.79

 Presidential

0.78

Activations Density 0.015%

mentions of political leaders, specifically Prime Ministers

references to political leaders, specifically prime ministers

No Comments

No Known Activations