INDEX

Explanations

words related to stoicism

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

URI

-0.76

 Pathfinder

-0.69

iott

-0.66

 Ancients

-0.64

 Triangle

-0.64

 spoilers

-0.61

 Memories

-0.60

gdala

-0.60

 Rend

-0.60

 accuracy

-0.60

POSITIVE LOGITS

pped

1.34

pping

1.28

ppy

1.25

pper

1.16

ven

1.09

ving

1.06

ppers

1.01

iety

1.01

oby

0.97

ppings

0.96

Activations Density 0.036%

words related to stoicism

No Comments

No Known Activations