INDEX

Explanations

references to specific monetary amounts

oai_token-act-pair · gpt-3.5-turbo

mentions of currency values, particularly in cents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Valhalla

-0.85

 skelet

-0.75

 GÃ¶

-0.68

 Dresden

-0.68

 Borg

-0.66

 à¨

-0.65

 Hussain

-0.63

Stud

-0.63

 Thrones

-0.63

 Stra

-0.63

POSITIVE LOGITS

 cents

1.24

 apiece

0.96

imet

0.87

imeter

0.80

 dollar

0.79

heet

0.77

 sterling

0.77

clair

0.75

uits

0.75

per

0.75

Activations Density 0.010%

references to specific monetary amounts

mentions of currency values, particularly in cents

No Comments

No Known Activations