INDEX

Explanations

information related to statistical margins of error

oai_token-act-pair · gpt-3.5-turbo

statistical terms related to margins of error and polling data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Merit

-0.73

APTER

-0.71

IRT

-0.69

Pg

-0.66

ãĥīãĥ©

-0.64

FTWARE

-0.64

 Trance

-0.63

Activity

-0.62

 Prol

-0.62

ĸļ

-0.62

POSITIVE LOGITS

+/-

1.19

 margin

1.04

 margins

1.04

 error

0.94

 rounding

0.93

 errors

0.91

 sampling

0.87

isSpecialOrderable

0.84

 Â±

0.82

 uncertainties

0.81

Activations Density 0.099%

information related to statistical margins of error

statistical terms related to margins of error and polling data

No Comments

No Known Activations