INDEX

Explanations

occurrences of numerical counts of people being affected by various events

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

tnc

-0.87

inventoryQuantity

-0.83

Emer

-0.69

Corp

-0.68

 srfAttach

-0.66

 Parables

-0.66

ebook

-0.65

 Sadd

-0.65

Dog

-0.64

catentry

-0.64

POSITIVE LOGITS

 smugglers

0.92

 gathered

0.88

uscript

0.86

 worldwide

0.85

 fleeing

0.83

 evacuated

0.82

 crammed

0.81

 displaced

0.80

ava

0.80

 perished

0.79

Activations Density 0.056%

occurrences of numerical counts of people being affected by various events

No Comments

No Known Activations