INDEX

Explanations

conditions set by specific criteria containing mathematical operations

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

 disg

-0.71

 Wikimedia

-0.68

 Canaver

-0.61

©¶æ¥µ

-0.60

bats

-0.59

esville

-0.58

avery

-0.58

 tirelessly

-0.56

 lending

-0.56

 prosecut

-0.56

POSITIVE LOGITS

==

1.29

&&

1.26

<=

1.21

!=

1.19

>=

1.16

||

1.10

eq

0.95

==

0.91

===

0.86

){

0.86

Activations Density 0.105%

conditions set by specific criteria containing mathematical operations

No Comments

No Known Activations