INDEX

Explanations

large numerical values or figures

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

ifice

-0.74

ivity

-0.69

krit

-0.68

iqu

-0.66

rival

-0.66

ournal

-0.63

venge

-0.63

ufact

-0.63

otto

-0.63

agon

-0.61

POSITIVE LOGITS

1.07

Hz

1.06

mAh

1.03

bps

0.94

Hz

0.93

lbs

0.88

lb

0.87

 miles

0.87

ppm

0.87

ths

0.87

Activations Density 0.077%

large numerical values or figures

No Comments

No Known Activations