INDEX

Explanations

phrases related to financial decisions and responsibilities

oai_token-act-pair · gpt-3.5-turbo

phrases associated with financial planning and savings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 likeness

-0.68

 Lavrov

-0.62

 degraded

-0.62

 Plaint

-0.62

paralle

-0.60

 eminent

-0.60

alion

-0.59

notations

-0.59

 implication

-0.57

 FISA

-0.57

POSITIVE LOGITS

 hobbies

1.08

 lifestyle

0.92

arenthood

0.91

 commuting

0.89

 commute

0.85

 vacations

0.84

 quitting

0.81

 compuls

0.81

 leisure

0.80

 binge

0.79

Activations Density 1.628%

phrases related to financial decisions and responsibilities

phrases associated with financial planning and savings

No Comments

No Known Activations