INDEX

Explanations

words related to medical research and immune system properties

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

bye

-0.55

loe

-0.54

nen

-0.53

Square

-0.53

cyl

-0.51

 Hover

-0.50

 Puzzles

-0.49

umbnail

-0.49

tsky

-0.48

uously

-0.48

POSITIVE LOGITS

enhagen

0.66

ochemistry

0.58

PsyNetMessage

0.57

forcement

0.53

omnia

0.53

 transpl

0.52

UNE

0.52

ersive

0.52

iferation

0.51

iries

0.50

Activations Density 16.009%

words related to medical research and immune system properties

No Comments

No Known Activations