INDEX

Explanations

statements of opinion or commentary on political events or individuals

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

ĪĴ

-1.13

CLASSIFIED

-1.03

ãĤ¡

-1.02

HAEL

-1.01

ãĥĻ

-1.01

=]

-1.01

matter

-1.00

 Thieves

-0.99

CVE

-0.99

\\\\\\\\

-0.96

POSITIVE LOGITS

wards

1.34

clusions

1.28

between

1.25

bound

1.18

roads

1.16

 unison

1.13

igious

1.10

 front

1.10

 accordance

1.09

 vivo

1.08

Activations Density 1.202%

statements of opinion or commentary on political events or individuals

No Comments

No Known Activations