INDEX

Explanations

phrases related to ethics, morality, and decision-making

oai_token-act-pair · gpt-3.5-turbo

expressions of concern or apprehension regarding social or legal issues

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

ãĤ´ãĥ³

-0.70

BuyableInstoreAndOnline

-0.66

 Bunker

-0.63

 Doodle

-0.61

 Slug

-0.59

ague

-0.58

ãĤ»

-0.57

Few

-0.57

antine

-0.57

odore

-0.56

POSITIVE LOGITS

 maybe

1.15

 somebody

1.03

 somehow

1.01

 gonna

0.97

 sort

0.90

uh

0.89

 potentially

0.88

 kind

0.86

 kinda

0.85

maybe

0.85

Activations Density 0.597%

phrases related to ethics, morality, and decision-making

expressions of concern or apprehension regarding social or legal issues

No Comments

No Known Activations