INDEX

Explanations

phrases related to working hard or working long hours

oai_token-act-pair · gpt-3.5-turbo

references to work and employment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

antha

-0.82

EStream

-0.71

 Ukrain

-0.70

 constitu

-0.69

leans

-0.65

cemic

-0.64

phies

-0.61

 Flavoring

-0.61

ulner

-0.60

emonic

-0.59

POSITIVE LOGITS

 overtime

1.10

 tirelessly

1.10

 diligently

0.97

 collabor

0.92

 harder

0.91

 ethic

0.89

 paycheck

0.86

 miracles

0.86

 remotely

0.85

aday

0.82

Activations Density 0.069%

phrases related to working hard or working long hours

references to work and employment

No Comments

No Known Activations