INDEX

Explanations

locations or events mentioned with a specific date or time

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ratulations

-0.75

uria

-0.69

vation

-0.67

notation

-0.67

scape

-0.66

eanor

-0.65

 survives

-0.65

ata

-0.64

 besides

-0.64

packages

-0.63

POSITIVE LOGITS

 behest

1.46

 outset

1.06

 expense

1.02

 helm

1.01

 forefront

0.98

 intersection

0.93

 height

0.91

end

0.89

 urging

0.88

 insistence

0.86

Activations Density 0.108%

locations or events mentioned with a specific date or time

instances of the word "the."

No Comments

No Known Activations