INDEX

Explanations

mentions of a specific location within a household

oai_token-act-pair · gpt-3.5-turbo

references to familial relationships and home

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.81

cale

-0.74

lda

-0.74

ãĥķãĤ©

-0.72

\\\\\\\\

-0.71

ãĤ´ãĥ³

-0.68

isexual

-0.68

srf

-0.68

DERR

-0.66

ICO

-0.66

POSITIVE LOGITS

 worn

0.74

 holder

0.73

 oneself

0.69

 belonging

0.68

 exercised

0.65

 belonged

0.63

 mailbox

0.62

 Scher

0.61

idable

0.60

 Reck

0.60

Activations Density 0.612%

mentions of a specific location within a household

references to familial relationships and home

No Comments

No Known Activations