INDEX

Explanations

action and movement-related words

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

 Scal

-0.43

tein

-0.42

 crossover

-0.41

 foreign

-0.41

ilege

-0.40

pri

-0.40

 href

-0.38

 vantage

-0.38

 relationship

-0.38

 specificity

-0.38

POSITIVE LOGITS

ntil

0.54

DAQ

0.52

 withd

0.51

 havoc

0.49

aneously

0.49

ikarp

0.48

 srfAttach

0.48

tics

0.47

retty

0.47

ãĢĤ

0.47

Activations Density 8.895%

action and movement-related words

No Comments

No Known Activations