INDEX

Explanations

names of locations or historical events, especially related to war or politics

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

 transpl

-0.80

 interpol

-0.80

cod

-0.79

 dart

-0.79

mot

-0.73

 partName

-0.72

 Phant

-0.72

 simul

-0.72

jug

-0.71

phony

-0.71

POSITIVE LOGITS

orage

1.10

atown

1.06

andise

1.05

amac

1.01

ione

0.93

ablishment

0.92

inese

0.92

 Cassidy

0.91

anwhile

0.90

atchewan

0.88

Activations Density 0.072%

names of locations or historical events, especially related to war or politics

No Comments

No Known Activations