INDEX

Explanations

negative constructions in sentences

oai_token-act-pair · gpt-4o-mini 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

velt

-0.76

tein

-0.72

FAQ

-0.72

irst

-0.68

hower

-0.67

irt

-0.66

ulty

-0.64

avi

-0.63

orter

-0.63

kamp

-0.63

POSITIVE LOGITS

 necessarily

1.56

epad

1.16

 bothering

1.02

icably

0.97

icable

0.94

 merely

0.94

ifies

0.92

eworthy

0.87

withstanding

0.84

ific

0.83

Activations Density 0.049%

negative constructions in sentences

No Comments

No Known Activations