INDEX

Explanations

proper names and nouns related to various subjects and entities

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

 Revel

-0.69

lain

-0.66

 Lies

-0.58

 Poverty

-0.58

 Heard

-0.57

 registrations

-0.57

 Democracy

-0.56

 Yanuk

-0.56

 Canterbury

-0.56

 Happiness

-0.56

POSITIVE LOGITS

ples

1.11

BILITY

1.02

BILITIES

0.98

pport

0.95

ptions

0.91

essen

0.88

verage

0.87

plom

0.87

zzle

0.87

ire

0.86

Activations Density 0.094%

proper names and nouns related to various subjects and entities

No Comments

No Known Activations