INDEX

Explanations

terms related to injustice or unfairness

oai_token-act-pair · gpt-3.5-turbo

words associated with injustice and unfair treatment

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

gdala

-0.95

yss

-0.80

á

-0.76

phrine

-0.74

aeda

-0.73

berman

-0.70

Downloadha

-0.70

 Enhancement

-0.70

 livest

-0.68

zzo

-0.67

POSITIVE LOGITS

ified

1.47

ifiable

1.46

ifier

0.97

ifiers

0.94

nesses

0.90

ification

0.86

ifying

0.86

IFIED

0.85

ly

0.84

ious

0.84

Activations Density 0.021%

terms related to injustice or unfairness

words associated with injustice and unfair treatment

No Comments

No Known Activations