INDEX

Explanations

mentions of the word "Stanford."

oai_token-act-pair · gpt-3.5-turbo

references to Stanford University

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

alez

-0.76

hops

-0.71

cedented

-0.70

unct

-0.68

ramid

-0.67

merce

-0.67

 substant

-0.66

usher

-0.65

interpret

-0.64

odic

-0.63

POSITIVE LOGITS

 Institution

1.06

 University

0.99

 Stanford

0.89

 Cardinal

0.88

 Hills

0.84

thal

0.82

 Alto

0.79

 Marriott

0.79

 Researchers

0.77

 Hanson

0.77

Activations Density 0.008%

mentions of the word "Stanford."

references to Stanford University

No Comments

No Known Activations