INDEX

Explanations

technical terms and references in a text, like names of people, locations, and specific events

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

ãħĭ

-0.38

ascript

-0.37

OSH

-0.37

olicy

-0.35

 gasp

-0.34

ggle

-0.30

 arresting

-0.30

_>

-0.30

ok

-0.30

------------------------------------------------

-0.30

POSITIVE LOGITS

ial

0.47

ship

0.46

raits

0.45

rent

0.44

IAL

0.42

istance

0.42

oulos

0.42

icated

0.41

alis

0.41

sburgh

0.40

Activations Density 10.433%

technical terms and references in a text, like names of people, locations, and specific events

No Comments

No Known Activations