INDEX

Explanations

instances where the text prompts the reader to print content

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Print" in various contexts related to publishing and sharing content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

hov

-0.78

rolet

-0.71

hunt

-0.71

hart

-0.70

asio

-0.65

onite

-0.65

 Alban

-0.62

nen

-0.61

verages

-0.60

axter

-0.59

POSITIVE LOGITS

able

0.83

 Print

0.81

outs

0.80

Print

0.80

âĢ¢âĢ¢âĢ¢âĢ¢

0.79

 print

0.78

Writer

0.77

out

0.77

print

0.77

 Seym

0.76

Activations Density 0.028%

instances where the text prompts the reader to print content

instances of the word "Print" in various contexts related to publishing and sharing content

No Comments

No Known Activations