INDEX

Explanations

phrases related to the formation of groups or entities, such as alliances or communities

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

reys

-0.92

rey

-0.79

visor

-0.79

ily

-0.79

yssey

-0.75

ILLE

-0.71

 untreated

-0.71

 avoided

-0.70

iolet

-0.70

iasis

-0.68

POSITIVE LOGITS

idable

1.39

ulates

1.38

ulas

1.31

aldehyde

1.25

ulating

1.24

ulate

1.15

 alliances

1.10

 Aires

1.08

furt

1.06

atter

1.05

Activations Density 8.481%

phrases related to the formation of groups or entities, such as alliances or communities

No Comments

No Known Activations