INDEX

Explanations

words related to UKIP, Nigel Farage, and MEPs

oai_token-act-pair · gpt-3.5-turbo

mentions of the UK Independence Party and its key figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Yosemite

-0.71

Yao

-0.70

ENE

-0.70

Iro

-0.69

efer

-0.67

 Yuan

-0.65

à¨

-0.65

Condition

-0.65

nesota

-0.65

âĶĢâĶĢ

-0.65

POSITIVE LOGITS

 Farage

1.17

MEP

1.09

 UKIP

0.93

 Ukip

0.92

 electorate

0.83

 Voters

0.78

 voters

0.77

istani

0.76

 elector

0.75

 colours

0.74

Activations Density 0.011%

words related to UKIP, Nigel Farage, and MEPs

mentions of the UK Independence Party and its key figures

No Comments

No Known Activations