INDEX

Explanations

the word "You"

oai_token-act-pair · gpt-3.5-turbo

the use of the word "You" or phrases that directly address the reader

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 airs

-0.63

ipal

-0.62

assembly

-0.61

 srfAttach

-0.58

ice

-0.58

 Commerce

-0.57

Lago

-0.57

actic

-0.57

éĹ

-0.56

 ammon

-0.56

POSITIVE LOGITS

're

1.43

've

1.26

'll

1.23

 guys

1.10

'd

1.05

tub

1.00

ngth

0.93

 gotta

0.92

ldon

0.91

ths

0.90

Activations Density 0.118%

the word "You"

the use of the word "You" or phrases that directly address the reader

No Comments

No Known Activations