INDEX

Explanations

acronyms or shorthand used to represent longer terms or phrases

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "or" indicating alternative options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

rue

-0.91

irms

-0.82

arten

-0.81

ires

-0.80

erest

-0.78

olicy

-0.78

eor

-0.77

tackle

-0.76

estern

-0.76

een

-0.76

POSITIVE LOGITS

 alternatively

1.03

chard

0.94

ifice

0.84

 whatever

0.82

 equival

0.82

GAN

0.79

 abbrevi

0.78

 equivalent

0.76

 perhaps

0.76

MAP

0.75

Activations Density 0.063%

acronyms or shorthand used to represent longer terms or phrases

phrases that include the word "or" indicating alternative options

No Comments

No Known Activations