INDEX

Explanations

mentions of future events or possibilities

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

assin

-0.63

 Dude

-0.59

galitarian

-0.57

 Madness

-0.57

unes

-0.57

ileaks

-0.54

Craft

-0.53

 messenger

-0.53

amps

-0.53

 Dove

-0.52

POSITIVE LOGITS

 hereafter

1.09

 continue

1.03

continue

0.99

 soon

0.97

 thereafter

0.94

 someday

0.93

soon

0.88

contin

0.85

 tomorrow

0.82

 eventually

0.81

Activations Density 0.384%

mentions of future events or possibilities

No Comments

No Known Activations