INDEX

Explanations

locations or specific place names that include the word "Mon" followed by a number

oai_token-act-pair · gpt-3.5-turbo

instances of the term "Mon" followed by various suffixes or additions

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

 Norn

-0.89

OHN

-0.87

éĹĺ

-0.80

æĸ¹

-0.78

ONSORED

-0.75

EXP

-0.74

ACTED

-0.74

ATING

-0.74

 Pathfinder

-0.73

enegger

-0.72

POSITIVE LOGITS

itored

1.19

olith

1.10

olithic

1.09

opoly

1.03

stros

1.02

astery

1.02

roe

0.97

ique

0.94

ero

0.91

soon

0.90

Activations Density 0.014%

locations or specific place names that include the word "Mon" followed by a number

instances of the term "Mon" followed by various suffixes or additions

No Comments

No Known Activations