INDEX

Explanations

statements containing the word "it" followed by a verb

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

fleet

-0.34

 Esther

-0.34

Et

-0.33

 Habit

-0.31

lette

-0.31

EMA

-0.29

 Jagu

-0.29

onica

-0.29

Americ

-0.28

Je

-0.28

POSITIVE LOGITS

 technically

0.45

 initially

0.40

 admittedly

0.38

 ostensibly

0.37

 admirable

0.36

 laud

0.35

 disagree

0.34

 sounds

0.34

 lacks

0.33

 sympath

0.32

Activations Density 10.084%

statements containing the word "it" followed by a verb

No Comments

No Known Activations