INDEX

Explanations

phrases and words that describe disparities, inequalities, or imbalances

oai_token-act-pair · gpt-3.5-turbo

instances of disparity or disproportionate impact on various groups or issues

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

uring

-0.80

ince

-0.74

erm

-0.73

love

-0.72

adal

-0.71

shire

-0.70

ures

-0.70

zyme

-0.69

psons

-0.69

DCS

-0.68

POSITIVE LOGITS

 disproportionately

0.93

 disproportion

0.92

 disadvantage

0.84

 disadvant

0.79

 favoring

0.78

 disenfranch

0.77

 disadvantages

0.74

 representation

0.72

aga

0.70

 benefiting

0.69

Activations Density 0.049%

phrases and words that describe disparities, inequalities, or imbalances

instances of disparity or disproportionate impact on various groups or issues

No Comments

No Known Activations