INDEX

Explanations

phrases related to factory operations

oai_token-act-pair · gpt-3.5-turbo

mentions of factories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

laus

-0.83

soever

-0.82

byss

-0.75

 Liberties

-0.72

vind

-0.71

partisan

-0.67

ĺħ

-0.66

lihood

-0.66

maxwell

-0.66

emonic

-0.66

POSITIVE LOGITS

 factory

0.88

actory

0.83

ounter

0.83

 Worker

0.82

orer

0.79

 worker

0.78

rador

0.76

worker

0.75

 farming

0.73

urers

0.72

Activations Density 0.021%

phrases related to factory operations

mentions of factories

No Comments

No Known Activations