INDEX

Explanations

references to or mentions of the country Norway

oai_token-act-pair · gpt-3.5-turbo

references to Norway

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

eers

-0.75

è¦ļéĨĴ

-0.64

INESS

-0.61

 Granger

-0.61

Excellent

-0.58

realDonaldTrump

-0.58

 Piercing

-0.58

AGES

-0.57

 administrations

-0.57

 Mushroom

-0.56

POSITIVE LOGITS

wegian

1.20

berto

1.08

phan

1.00

wich

0.99

pheus

0.99

thodox

0.97

cht

0.95

ris

0.89

rien

0.89

rils

0.86

Activations Density 0.010%

references to or mentions of the country Norway

references to Norway

No Comments

No Known Activations