INDEX

Explanations

words related to mentorship and mentoring

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

•Layer 6 UMAP region: Mixed in middle - local

No Comments

Negative Logits

Ô

-0.46

Dim

-0.45

 Convention

-0.37

 Hebdo

-0.36

NX

-0.36

 daylight

-0.36

 WATCHED

-0.35

 dism

-0.34

 guessing

-0.34

rencies

-0.34

POSITIVE LOGITS

orship

0.76

 ment

0.63

oring

0.62

 mentors

0.61

 mentor

0.60

ored

0.58

 Ment

0.57

iors

0.55

enge

0.54

lasses

0.53

Activations Density 6.222%

words related to mentorship and mentoring

No Comments

No Known Activations