INDEX

Explanations

names and titles in a political context

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

-1.28

ed

-1.15

ean

-1.09

hips

-1.09

fax

-1.08

ships

-1.08

rett

-1.05

ei

-1.04

esian

-1.03

aan

-1.02

POSITIVE LOGITS

atform

1.43

iqueness

1.35

cers

1.27

asion

1.23

okia

1.22

selves

1.18

merce

1.15

issan

1.14

ggle

1.10

yssey

1.08

Activations Density 2.843%

names and titles in a political context

No Comments

No Known Activations