INDEX

Explanations

mentions of the word "same."

oai_token-act-pair · gpt-3.5-turbo

references to same-sex marriage

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

erest

-0.71

OST

-0.71

arest

-0.71

 Bulg

-0.70

Bei

-0.65

ostic

-0.65

ASE

-0.65

åĩ

-0.64

efully

-0.63

liest

-0.63

POSITIVE LOGITS

 vein

0.79

rity

0.76

fam

0.74

bilt

0.69

sex

0.69

gender

0.68

 exact

0.68

ials

0.65

 sorts

0.64

Day

0.63

Activations Density 0.024%

mentions of the word "same."

references to same-sex marriage

No Comments

No Known Activations