INDEX

Explanations

statistics or facts about different types of people or populations

oai_token-act-pair · gpt-3.5-turbo

references to average individuals and their behaviors or experiences

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

metadata

-0.79

 engines

-0.72

 incorporation

-0.72

 divisions

-0.72

utherland

-0.70

 deletion

-0.69

 ingred

-0.68

 forfeiture

-0.67

 domains

-0.66

 arrangements

-0.66

POSITIVE LOGITS

who

1.00

who

0.83

 dared

0.73

 farmer

0.73

 whom

0.72

 believer

0.72

 whose

0.72

athon

0.71

hawk

0.71

 thinks

0.69

Activations Density 0.575%

statistics or facts about different types of people or populations

references to average individuals and their behaviors or experiences

No Comments

No Known Activations