INDEX

Explanations

mentions of the Academy Award, colloquially known as the "Oscar", in texts

oai_token-act-pair · gpt-3.5-turbo

references to the Academy Awards, specifically mentions of "Oscar"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

plain

-0.68

BOOK

-0.67

INESS

-0.67

ears

-0.66

walking

-0.65

manship

-0.64

DCS

-0.61

 subsistence

-0.59

minist

-0.59

 Wildcats

-0.59

POSITIVE LOGITS

 Wilde

1.07

 Oscar

0.91

 Awards

0.88

 Nebula

0.81

vine

0.81

inal

0.78

 nominations

0.78

gio

0.78

 laure

0.75

 Mayer

0.73

Activations Density 0.006%

mentions of the Academy Award, colloquially known as the "Oscar", in texts

references to the Academy Awards, specifically mentions of "Oscar"

No Comments

No Known Activations