INDEX

Explanations

words related to impact or significant effects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

creen

-0.74

brates

-0.70

vironment

-0.68

brate

-0.66

lihood

-0.65

 Lobby

-0.64

 Tile

-0.63

sbm

-0.63

blance

-0.62

FORE

-0.62

POSITIVE LOGITS

romptu

1.32

ossibly

1.32

orters

1.25

regn

1.23

urities

1.22

orter

1.21

otent

1.18

ulsive

1.18

ressing

1.13

assion

1.09

Activations Density 0.005%

words related to impact or significant effects

No Comments

No Known Activations