INDEX

Explanations

names of political leaders, particularly Prime Ministers

oai_token-act-pair · gpt-3.5-turbo

references to prime ministers

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

anwhile

-0.80

ersion

-0.77

ologies

-0.75

aneers

-0.75

ript

-0.75

entric

-0.74

avery

-0.74

bleacher

-0.73

ciplinary

-0.73

adr

-0.72

POSITIVE LOGITS

 Minister

1.15

 ministerial

0.99

 Ministers

0.95

 minister

0.91

 ministers

0.88

 Directive

0.85

Rib

0.83

Prime

0.81

 Recep

0.81

 Prime

0.79

Activations Density 0.012%

names of political leaders, particularly Prime Ministers

references to prime ministers

No Comments

No Known Activations