INDEX

Explanations

phrases related to community impact, economic improvement, and equality

oai_token-act-pair · gpt-3.5-turbo

references to building a better society and economy for everyone

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

canon

-0.77

pmwiki

-0.68

kered

-0.67

arin

-0.67

arro

-0.64

argon

-0.63

ado

-0.62

obook

-0.61

SpaceEngineers

-0.60

 guesses

-0.59

POSITIVE LOGITS

 Communities

0.89

 workforce

0.85

 communities

0.83

 empowerment

0.82

 Indigenous

0.80

 lifestyles

0.79

 grassroots

0.79

 dignity

0.77

 economically

0.76

 disadvantaged

0.75

Activations Density 1.137%

phrases related to community impact, economic improvement, and equality

references to building a better society and economy for everyone

No Comments

No Known Activations