INDEX

Explanations

data related to statistics, rankings, and numerical values across various categories

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

Data Type

torch.float32

Hook Point

blocks.8.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

ĪĴ

-0.74

hement

-0.73

©¶æ

-0.69

çīĪ

-0.68

pecially

-0.68

rog

-0.67

nik

-0.67

western

-0.66

chool

-0.64

haven

-0.64

POSITIVE LOGITS

 total

1.28

 percentage

1.28

 allowable

1.22

 number

1.21

 amount

1.20

 calories

1.19

 mileage

1.18

GDP

1.15

 throughput

1.14

 value

1.10

Activations Density 2.995%

data related to statistics, rankings, and numerical values across various categories

No Comments

No Known Activations