INDEX

Explanations

locations or places

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

thood

-0.88

xual

-0.68

natureconservancy

-0.66

versive

-0.65

rez

-0.64

ullivan

-0.64

erer

-0.64

erity

-0.63

xon

-0.61

ertodd

-0.61

POSITIVE LOGITS

 Calif

1.26

 Colo

1.11

TX

1.03

 Tenn

1.01

Fla

1.01

TN

1.00

Md

0.99

 Illinois

0.97

KY

0.96

 California

0.94

Activations Density 1.229%

locations or places

No Comments

No Known Activations