INDEX

Explanations

places or locations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lli

-0.69

eur

-0.66

ModLoader

-0.63

 Advertisement

-0.61

iveness

-0.60

chester

-0.60

âĢ¢âĢ¢âĢ¢âĢ¢

-0.59

 Chronicle

-0.59

 preserves

-0.58

teen

-0.58

POSITIVE LOGITS

owitz

0.94

iewicz

0.89

hof

0.87

owsky

0.79

VD

0.78

olk

0.77

Osw

0.76

inki

0.76

achev

0.74

itant

0.74

Activations Density 0.042%

places or locations

No Comments

No Known Activations