INDEX

Explanations

terms related to sexual orientations, specifically focusing on identifying words related to bisexual individuals

oai_token-act-pair · gpt-3.5-turbo

references to bisexuality and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Eat

-0.83

EMS

-0.76

LV

-0.71

keeper

-0.68

 Yard

-0.67

urers

-0.65

steen

-0.64

witz

-0.64

bilt

-0.63

hunt

-0.62

POSITIVE LOGITS

ity

1.18

iliary

0.88

ities

0.84

dar

0.81

iated

0.80

 citiz

0.80

 bisexual

0.80

iliated

0.79

isexual

0.75

inals

0.74

Activations Density 0.026%

terms related to sexual orientations, specifically focusing on identifying words related to bisexual individuals

references to bisexuality and related concepts

No Comments

No Known Activations