INDEX

Explanations

references to UK Prime Minister Theresa May

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Theresa May."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

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

assian

-0.71

esville

-0.68

isode

-0.68

vernment

-0.65

 Honolulu

-0.65

 americ

-0.64

oned

-0.64

anza

-0.63

ysis

-0.61

matic

-0.61

POSITIVE LOGITS

 Sturgeon

0.94

May

0.94

 Downing

0.93

 Theresa

0.87

 Corbyn

0.86

 Clarkson

0.81

 Hunt

0.80

 Thatcher

0.80

 Rudd

0.80

May

0.78

Activations Density 0.046%

references to UK Prime Minister Theresa May

mentions of the name "Theresa May."

No Comments

No Known Activations