INDEX

Explanations

technology-related terms such as autonomous vehicles, artificial intelligence, and automation

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

cake

-0.83

wick

-0.81

pite

-0.78

fam

-0.77

oire

-0.76

 McGr

-0.73

iatus

-0.73

wy

-0.72

coe

-0.72

 Hick

-0.71

POSITIVE LOGITS

 bots

0.99

onomous

0.97

 neural

0.94

 algorithms

0.93

 robot

0.93

 robotic

0.93

 robots

0.89

 Neural

0.87

 programmed

0.86

 locom

0.83

Activations Density 1.081%

technology-related terms such as autonomous vehicles, artificial intelligence, and automation

No Comments

No Known Activations