INDEX

Explanations

names or terms related to the LGBTQ+ community, specifically focusing on the term "Gay."

oai_token-act-pair · gpt-3.5-turbo

references to the term "Gay"

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

arily

-0.78

igslist

-0.75

yrim

-0.75

umbing

-0.74

uncture

-0.69

 stockp

-0.69

 payable

-0.69

IBLE

-0.68

ocobo

-0.68

 conclud

-0.67

POSITIVE LOGITS

nor

1.07

lord

1.01

bian

0.98

rier

0.97

lyn

0.96

dar

0.91

ther

0.88

lene

0.86

 Marriage

0.86

zilla

0.85

Activations Density 0.012%

names or terms related to the LGBTQ+ community, specifically focusing on the term "Gay."

references to the term "Gay"

No Comments

No Known Activations