INDEX

Explanations

words related to physical impact or force

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Emin

-1.04

BuyableInstoreAndOnline

-0.97

uve

-0.89

umbn

-0.87

afety

-0.84

 abund

-0.84

ancies

-0.84

 Sins

-0.80

è¯

-0.80

 Debor

-0.79

POSITIVE LOGITS

starter

1.60

strap

1.31

starting

1.23

boxing

1.21

started

1.20

start

1.12

tails

1.03

 butt

0.97

haw

0.95

backs

0.94

Activations Density 8.926%

words related to physical impact or force

No Comments

No Known Activations