INDEX

Explanations

occurrences of the word "Min" followed by particular letters or digits

oai_token-act-pair · gpt-3.5-turbo

references to the character "Minnie" from popular media

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.89

 Compass

-0.77

schild

-0.72

 Odyssey

-0.63

 NETWORK

-0.62

 Clyde

-0.62

 Cascade

-0.61

 Indra

-0.61

red

-0.61

 mirrored

-0.61

POSITIVE LOGITS

iatures

1.20

neapolis

1.18

nesota

1.13

imal

1.12

erva

1.09

utes

1.07

otaur

1.03

imize

1.01

oan

1.00

usc

0.99

Activations Density 0.015%

occurrences of the word "Min" followed by particular letters or digits

references to the character "Minnie" from popular media

No Comments

No Known Activations