INDEX

Explanations

names of people

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

ATIONS

-0.67

 hindsight

-0.64

ISION

-0.64

 depreciation

-0.63

 shootout

-0.62

 visionary

-0.62

 Corsair

-0.61

 erection

-0.60

 Provincial

-0.60

Excellent

-0.59

POSITIVE LOGITS

 herself

1.10

ova

0.87

otte

0.87

 miscar

0.86

thia

0.85

rigan

0.83

fet

0.81

 bikini

0.80

lette

0.80

 breasts

0.79

Activations Density 0.181%

names of people

No Comments

No Known Activations