INDEX

Explanations

the word "may" followed by a verb indicating a possibility or potential action

oai_token-act-pair · gpt-3.5-turbo

occurrences of the words "may" and "might," indicating possibility or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 sorted

-0.69

 solid

-0.67

 ever

-0.66

 career

-0.65

 starters

-0.65

 straight

-0.64

 breakdown

-0.64

 vertical

-0.63

 shut

-0.61

 clean

-0.60

POSITIVE LOGITS

may

4.26

might

1.91

May

1.58

shall

1.55

MAY

1.52

must

1.51

could

1.31

will

1.25

should

1.20

can

1.13

Activations Density 0.008%

the word "may" followed by a verb indicating a possibility or potential action

occurrences of the words "may" and "might," indicating possibility or uncertainty

No Comments

No Known Activations