INDEX

Explanations

first person singular verbs and personal experiences

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

assis

-0.51

bour

-0.50

heter

-0.48

 Analy

-0.45

Fram

-0.44

 propensity

-0.44

 awaiting

-0.43

 reigning

-0.43

 anticipating

-0.43

enhagen

-0.43

POSITIVE LOGITS

 sure

0.76

hift

0.74

netflix

0.61

 landfall

0.60

 headlines

0.59

 sense

0.56

URE

0.56

ailable

0.56

escape

0.56

fun

0.55

Activations Density 10.098%

first person singular verbs and personal experiences

No Comments

No Known Activations