INDEX

Explanations

words ending in "-or"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "or"

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

OTAL

-0.68

inctions

-0.59

SPA

-0.57

SPONSORED

-0.56

 rounded

-0.56

eas

-0.56

Sus

-0.55

£ı

-0.54

 msec

-0.54

eenth

-0.53

POSITIVE LOGITS

chid

1.15

ific

1.12

izons

1.06

ussia

1.03

ikawa

1.02

phans

1.01

andom

1.01

onto

1.00

thodox

0.99

bid

0.95

Activations Density 0.040%

words ending in "-or"

instances of the word "or"

No Comments

No Known Activations