INDEX

Explanations

proper nouns and names related to politics, individuals, and locations

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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

olitics

-0.55

lihood

-0.48

peed

-0.47

/-

-0.46

rology

-0.46

chal

-0.45

fruit

-0.44

noon

-0.43

nerg

-0.43

LEASE

-0.43

POSITIVE LOGITS

 Soup

0.64

gren

0.56

otte

0.56

 Newman

0.56

iac

0.55

anooga

0.55

ibur

0.54

pton

0.52

sburgh

0.49

 Campbell

0.48

Activations Density 8.346%

proper nouns and names related to politics, individuals, and locations

No Comments

No Known Activations

proper nouns and names related to politics, individuals, and locations

No Comments

No Known Activations