INDEX

Explanations

references to the location "Lo"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Lo" 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 @ 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

manship

-0.93

itated

-0.73

ãĥĩ

-0.73

*/(

-0.72

sonian

-0.72

ä»£

-0.69

ãĤ¼ãĤ¦ãĤ¹

-0.69

sburg

-0.68

ITAL

-0.68

ãĥ¼ãĥĨãĤ£

-0.66

POSITIVE LOGITS

veland

1.19

zzle

1.14

zzi

1.06

oser

1.05

fty

1.05

vers

1.03

aned

1.03

ose

0.99

ven

0.97

pper

0.96

Activations Density 0.013%

references to the location "Lo"

mentions of the name "Lo" in various contexts

No Comments

No Known Activations