INDEX

Explanations

references to geopolitics, military conflicts, and political figures

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

thood

-0.79

 besides

-0.76

 without

-0.75

 because

-0.73

eno

-0.71

verage

-0.70

leeve

-0.69

 differs

-0.68

rade

-0.68

 anyways

-0.65

POSITIVE LOGITS

 latter

1.34

 oldest

1.30

 largest

1.29

 longest

1.25

 smallest

1.20

 biggest

1.19

 fastest

1.15

 earliest

1.15

 latest

1.14

 youngest

1.12

Activations Density 1.111%

references to geopolitics, military conflicts, and political figures

No Comments

No Known Activations