INDEX

Explanations

adjectives and phrases related to suitability or fit for various situations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ancies

-0.71

 clipboard

-0.61

arthed

-0.52

noxious

-0.51

 unexplained

-0.50

usters

-0.50

facts

-0.50

 registry

-0.49

 pudding

-0.49

dust

-0.49

POSITIVE LOGITS

 considering

0.57

anke

0.57

ahime

0.57

ãĤ¢ãĥ«

0.56

wark

0.54

ovie

0.54

 opener

0.52

PsyNetMessage

0.52

isphere

0.51

ella

0.51

Activations Density 7.579%

adjectives and phrases related to suitability or fit for various situations

No Comments

No Known Activations