INDEX

Explanations

phrases related to government policies, international relations, and political events

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

interstitial

-1.24

PET

-1.09

cious

-1.00

esa

-0.99

ioned

-0.94

staking

-0.93

phrine

-0.92

inski

-0.91

onding

-0.89

Else

-0.88

POSITIVE LOGITS

stretched

1.54

ta

1.36

rage

1.34

fitted

1.26

doors

1.23

lier

1.22

posts

1.20

casts

1.17

smart

1.14

door

1.06

Activations Density 0.475%

phrases related to government policies, international relations, and political events

No Comments

No Known Activations