INDEX

Explanations

book and movie titles

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

 arsen

-0.86

ittal

-0.81

 wiser

-0.70

xon

-0.68

itals

-0.68

ioned

-0.67

ront

-0.66

ogeneity

-0.65

amination

-0.64

hap

-0.64

POSITIVE LOGITS

 Remastered

0.92

ONSORED

0.91

 Volume

0.87

[|

0.84

feat

0.84

 Featuring

0.81

 Redux

0.80

Premium

0.78

Ħ¢

0.71

 Definitive

0.70

Activations Density 2.030%

book and movie titles

No Comments

No Known Activations