INDEX

Explanations

spoilers in text

oai_token-act-pair · gpt-3.5-turbo

alerts and warnings regarding spoilers in media content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

undai

-0.71

 Palest

-0.70

llan

-0.69

reb

-0.68

trak

-0.67

artney

-0.66

Motion

-0.64

aepernick

-0.63

arov

-0.63

ADRA

-0.63

POSITIVE LOGITS

 spoiler

0.90

 SECTION

0.85

 spoil

0.83

 alert

0.83

 spoilers

0.82

 abound

0.81

 warning

0.80

OIL

0.78

 Warning

0.77

 Ahead

0.76

Activations Density 0.086%

spoilers in text

alerts and warnings regarding spoilers in media content

No Comments

No Known Activations