INDEX

Explanations

people related to specific events or locations

oai_token-act-pair · gpt-3.5-turbo

references to various groups of people involved in social or political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

inventoryQuantity

-0.74

Market

-0.69

 Euph

-0.68

cknow

-0.65

":"/

-0.64

 Thrones

-0.63

à¤

-0.63

Leader

-0.62

 Reign

-0.61

osterone

-0.59

POSITIVE LOGITS

 apiece

0.98

 crammed

0.95

who

0.88

 whom

0.87

hips

0.87

 indicted

0.86

 perished

0.85

 gathered

0.83

 vying

0.81

 kidnapped

0.81

Activations Density 0.265%

people related to specific events or locations

references to various groups of people involved in social or political contexts

No Comments

No Known Activations