INDEX

Explanations

instances of the word "Pe" followed by some context

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific individual or character, particularly variations of the name "Pe."

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

 overload

-0.67

Domain

-0.66

oldown

-0.65

fix

-0.63

 euth

-0.62

USS

-0.61

erer

-0.61

 dors

-0.61

ront

-0.61

ãĤ¢ãĥ«

-0.60

POSITIVE LOGITS

Pe

3.59

Pe

2.40

pe

1.64

pe

1.51

 peas

1.50

PE

1.39

 Pear

1.30

 Pepper

1.27

 Peach

1.21

 peanut

1.19

Activations Density 0.018%

instances of the word "Pe" followed by some context

mentions of a specific individual or character, particularly variations of the name "Pe."

No Comments

No Known Activations