INDEX

Explanations

keywords related to the real estate and construction industry, particularly focusing on condominiums

oai_token-act-pair · gpt-3.5-turbo

specific nouns related to various contexts, particularly architectural terms and catastrophic events

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Nap

-0.75

iT

-0.72

Ros

-0.72

BIT

-0.70

OVER

-0.69

OSP

-0.69

Pir

-0.68

Journal

-0.68

Veter

-0.66

Pak

-0.66

POSITIVE LOGITS

phrine

0.84

clude

0.79

 tails

0.72

kered

0.70

zed

0.67

zes

0.66

ization

0.65

 affair

0.65

ary

0.64

ced

0.64

Activations Density 0.239%

keywords related to the real estate and construction industry, particularly focusing on condominiums

specific nouns related to various contexts, particularly architectural terms and catastrophic events

No Known Activations