INDEX

Explanations

locations or geopolitical events mentioned in news articles

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

ĪĴ

-0.67

 Notting

-0.64

Balt

-0.61

[*]

-0.60

mony

-0.60

 duct

-0.60

CBI

-0.59

 lodging

-0.59

blooded

-0.59

 questioning

-0.57

POSITIVE LOGITS

intosh

0.93

gage

0.87

agement

0.80

ufact

0.78

adden

0.75

ONEY

0.75

nih

0.75

ICAN

0.75

estic

0.73

nesota

0.72

Activations Density 2.979%

locations or geopolitical events mentioned in news articles

No Comments

No Known Activations

locations or geopolitical events mentioned in news articles

No Comments

No Known Activations