INDEX

Explanations

terms related to historical events or notable figures

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

aber

-0.93

iggurat

-0.81

crew

-0.79

word

-0.76

apo

-0.75

ename

-0.74

ivery

-0.73

MpServer

-0.72

ibling

-0.71

liga

-0.71

POSITIVE LOGITS

 Shaun

1.11

 extraord

1.04

 Stephen

1.03

 Tony

1.02

 Nathan

1.00

 Erik

1.00

 Colin

0.99

 David

0.97

 Karl

0.97

 Gina

0.96

Activations Density 17.974%

terms related to historical events or notable figures

No Comments

No Known Activations