INDEX

Explanations

phrases related to analyzing situations or status

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Thoughts

-0.67

 guessing

-0.62

 Landing

-0.58

hips

-0.57

Mech

-0.56

 Bott

-0.56

ONE

-0.55

 typing

-0.55

 Synd

-0.55

 Speaking

-0.55

POSITIVE LOGITS

 spans

1.09

 encompasses

1.06

 includes

1.00

 extends

0.99

 resembles

0.95

 celebrates

0.94

 consumes

0.94

 comprises

0.93

 hasn

0.91

 embodies

0.91

Activations Density 0.174%

phrases related to analyzing situations or status

No Comments

No Known Activations