INDEX

Explanations

references to numerical information or statistical data

oai_token-act-pair · gpt-3.5-turbo

phrases or statements that convey uncertainty or potential outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 tremend

-0.79

 proport

-0.78

 exha

-0.67

 occas

-0.66

 eleph

-0.63

aditional

-0.63

 footing

-0.61

 authentic

-0.61

 belonging

-0.61

 engagements

-0.60

POSITIVE LOGITS

advertisement

0.99

ÂłÂłÂłÂłÂłÂłÂłÂł

0.98

posted

0.92

ÂłÂłÂłÂł

0.90

ÂłÂłÂł

0.86

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.86

Advertisement

0.82

Anyway

0.81

Posted

0.80

Article

0.79

Activations Density 0.499%

references to numerical information or statistical data

phrases or statements that convey uncertainty or potential outcomes

No Comments

No Known Activations