INDEX

Explanations

phrases related to divisions or separations

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

leeve

-0.76

ITNESS

-0.70

ensitivity

-0.66

elin

-0.65

ORTS

-0.65

CLA

-0.64

haw

-0.64

trak

-0.63

dding

-0.63

oken

-0.62

POSITIVE LOGITS

 hairs

0.99

 evenly

0.91

iple

0.91

 between

0.79

 divided

0.78

 apart

0.76

 into

0.74

oslav

0.74

ãĥĥãĥī

0.72

naire

0.72

Activations Density 0.035%

phrases related to divisions or separations

No Comments

No Known Activations