INDEX

Explanations

references to the United Kingdom (UK)

oai_token-act-pair · gpt-3.5-turbo

mentions of the UK

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cler

-0.84

ients

-0.83

utics

-0.81

iasis

-0.77

apego

-0.73

utic

-0.72

oso

-0.71

sbm

-0.71

etsk

-0.71

ovie

-0.70

POSITIVE LOGITS

 Parliament

1.00

RA

1.00

 Columbia

0.89

 Independence

0.87

 Columb

0.85

 Isles

0.79

Â£

0.79

 Government

0.78

 Crown

0.78

 Treasury

0.78

Activations Density 0.024%

references to the United Kingdom (UK)

mentions of the UK

No Comments

No Known Activations