INDEX

Explanations

phrases related to locations in North America

oai_token-act-pair · gpt-3.5-turbo

references to North America and its related contexts

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

raph

-0.88

bern

-0.77

atin

-0.74

gerald

-0.74

manager

-0.74

regor

-0.70

cop

-0.70

cellent

-0.69

notations

-0.69

notes

-0.68

POSITIVE LOGITS

 Federation

0.78

 bound

0.76

 Network

0.73

 Networks

0.72

 continent

0.71

 Syndrome

0.70

 Gazette

0.70

 Finals

0.69

 Distribution

0.67

 Championships

0.66

Activations Density 0.032%

phrases related to locations in North America

references to North America and its related contexts

No Comments

No Known Activations