INDEX

Explanations

phrases related to costs or negative consequences

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

riter

-1.13

mberg

-1.13

iferation

-1.08

anche

-1.06

ondon

-1.04

gon

-1.03

dit

-1.02

uggle

-1.02

umbn

-1.00

intend

-0.99

POSITIVE LOGITS

 downside

1.16

liest

1.15

 sidel

1.14

lier

1.06

 inflicted

1.04

 losses

1.02

ãĥ©ãĥ³

1.01

 incurred

1.01

 losers

1.01

SPONSORED

1.01

Activations Density 1.073%

phrases related to costs or negative consequences

No Comments

No Known Activations