INDEX

Explanations

mentions of specific network shows like A&E or characters from specific companies along with descriptions of operational features

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

Ã§

-0.85

pard

-0.83

taboola

-0.78

onen

-0.73

wcs

-0.73

fif

-0.71

thumbnails

-0.70

itu

-0.70

ãĥķ

-0.70

dayName

-0.69

POSITIVE LOGITS

 Networks

0.87

 alum

0.73

 guru

0.73

 Club

0.72

 Awards

0.72

 sessions

0.72

 Suite

0.70

 chiefs

0.70

 Mobility

0.69

 Summit

0.69

Activations Density 0.047%

mentions of specific network shows like A&E or characters from specific companies along with descriptions of operational features

No Comments

No Known Activations