INDEX

Explanations

phrases related to future time frames

oai_token-act-pair · gpt-3.5-turbo

mentions of future events or time frames

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

paio

-0.83

ooters

-0.83

mel

-0.82

cius

-0.81

olkien

-0.80

uca

-0.78

inet

-0.78

gor

-0.77

ording

-0.75

wright

-0.75

POSITIVE LOGITS

 weeks

1.12

 months

1.02

 days

1.02

 generations

0.98

 attractions

0.89

 week

0.85

 editions

0.83

 years

0.81

 edition

0.80

 installment

0.80

Activations Density 0.022%

phrases related to future time frames

mentions of future events or time frames

No Comments

No Known Activations