INDEX

Explanations

words related to extreme or intense emotions or descriptions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "freak" and its variations along with expressions of intensity or emotional response

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adr

-0.88

eger

-0.79

ournal

-0.73

akespeare

-0.68

fman

-0.68

İĭ

-0.67

 conduc

-0.67

dated

-0.66

cript

-0.66

rons

-0.66

POSITIVE LOGITS

ishly

1.27

ously

0.87

onom

0.86

 freak

0.81

wart

0.79

fuck

0.79

bum

0.76

ulously

0.74

istically

0.73

iness

0.73

Activations Density 0.008%

words related to extreme or intense emotions or descriptions

instances of the word "freak" and its variations along with expressions of intensity or emotional response

No Comments

No Known Activations