INDEX

Explanations

mentions of social or legal constructs and regulations

oai_token-act-pair · gpt-3.5-turbo

words indicating relationship statuses and regulatory concepts

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

adan

-0.91

utra

-0.87

osate

-0.81

adra

-0.80

achu

-0.76

ocene

-0.76

eus

-0.74

yip

-0.73

 Tycoon

-0.72

è£ħ

-0.71

POSITIVE LOGITS

 ones

0.83

paren

0.82

eals

0.72

 versions

0.72

 persons

0.71

ness

0.71

 goods

0.69

 objects

0.69

 foreign

0.68

 lung

0.66

Activations Density 0.267%

mentions of social or legal constructs and regulations

words indicating relationship statuses and regulatory concepts

No Comments

No Known Activations