INDEX

Explanations

proper names related to businesses or people

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Mur" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Pixie

-0.70

ISM

-0.68

 Gutenberg

-0.65

 Universities

-0.64

 Prometheus

-0.63

 Sector

-0.63

 OECD

-0.63

 Unch

-0.63

 Primal

-0.62

BOOK

-0.62

POSITIVE LOGITS

mur

1.22

geon

1.07

nit

1.01

rats

0.98

anda

0.98

abit

0.95

phys

0.95

asaki

0.92

ascus

0.92

ricane

0.91

Activations Density 0.015%

proper names related to businesses or people

occurrences of the name "Mur" in various contexts

No Comments

No Known Activations