INDEX

Explanations

locations or places

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

 seiz

-0.69

uously

-0.65

 contrace

-0.63

 acute

-0.62

 specificity

-0.61

 detectable

-0.60

 setbacks

-0.60

OTOS

-0.59

osponsors

-0.58

 severity

-0.58

POSITIVE LOGITS

velt

1.11

heid

0.81

issance

0.81

phant

0.78

stown

0.76

claw

0.74

estern

0.73

 Janeiro

0.73

merce

0.73

 Alto

0.72

Activations Density 0.116%

locations or places

No Comments

No Known Activations