INDEX

Explanations

statistical values such as margins of error

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to statistical margins of error

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

iru

-0.84

framework

-0.79

ukong

-0.78

gdala

-0.77

driving

-0.77

milo

-0.77

venge

-0.75

dor

-0.74

yz

-0.74

ulic

-0.73

POSITIVE LOGITS

TBA

0.99

NEC

0.85

CV

0.80

-------

0.79

+/-

0.78

AUD

0.75

TBD

0.75

 approx

0.73

 caveats

0.71

 embargo

0.71

Activations Density 0.571%

statistical values such as margins of error

terms and phrases related to statistical margins of error

No Comments

No Known Activations