INDEX

Explanations

mentions of CEOs and executives in various contexts, possibly related to corporate affairs

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

tro

-1.17

opter

-1.14

theless

-1.06

ivari

-1.03

wikipedia

-1.02

nia

-1.02

adoes

-1.02

stress

-0.99

ague

-0.98

ulia

-0.95

POSITIVE LOGITS

doms

1.25

 Doodle

1.10

IAL

1.08

 Larry

1.03

 executives

1.00

HAEL

0.95

 headquarters

0.94

Rex

0.93

 Marcus

0.92

 Mansion

0.92

Activations Density 0.958%

mentions of CEOs and executives in various contexts, possibly related to corporate affairs

No Comments

No Known Activations