INDEX

Explanations

phrases related to specific locations or organizations like "Union Square" and "Union of Progressive Peoples"

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

etsk

-0.77

olitics

-0.74

eger

-0.74

Ħ¢

-0.73

aunder

-0.71

Downloadha

-0.66

Ö¼

-0.65

apons

-0.63

 Remastered

-0.63

ographies

-0.62

POSITIVE LOGITS

 Carb

0.81

ships

0.80

 Confederation

0.79

pee

0.76

ship

0.76

idas

0.74

itas

0.73

ist

0.72

Leader

0.71

ism

0.70

Activations Density 0.024%

phrases related to specific locations or organizations like "Union Square" and "Union of Progressive Peoples"

No Comments

No Known Activations