INDEX

Explanations

phrases indicating urgency or importance

oai_token-act-pair · gpt-3.5-turbo

the imperative "Must" signaling urgency or recommendation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

vironment

-0.81

gdala

-0.78

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.76

foreseen

-0.73

EStreamFrame

-0.72

iency

-0.68

vernment

-0.68

 Catalyst

-0.67

MpServer

-0.66

tions

-0.64

POSITIVE LOGITS

hew

0.83

afa

0.83

 obey

0.80

aches

0.78

angs

0.78

ela

0.77

 comply

0.77

aqu

0.76

reads

0.74

zech

0.74

Activations Density 0.020%

phrases indicating urgency or importance

the imperative "Must" signaling urgency or recommendation

No Comments

No Known Activations