INDEX

Explanations

numbers at the end of a word or phrase

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

emi

-0.74

enger

-0.73

idious

-0.68

eval

-0.67

election

-0.67

hee

-0.65

ellen

-0.65

 purse

-0.64

eta

-0.64

pak

-0.64

POSITIVE LOGITS

yard

1.03

batch

0.93

jack

0.80

deen

0.80

parts

0.80

gence

0.79

tyard

0.78

cake

0.76

yards

0.76

lin

0.74

Activations Density 0.040%

numbers at the end of a word or phrase

No Comments

No Known Activations