INDEX

Explanations

phrases related to repeating actions or statements

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

anchester

-0.58

incinn

-0.58

-0.55

 Theft

-0.54

ubi

-0.53

ghai

-0.53

heading

-0.53

imo

-0.52

assis

-0.52

ima

-0.52

POSITIVE LOGITS

etheless

0.72

)=(

0.66

entimes

0.63

theless

0.53

 alike

0.52

 pellets

0.52

 mascara

0.51

 repeated

0.51

rely

0.51

 repetitive

0.50

Activations Density 7.138%

phrases related to repeating actions or statements

No Comments

No Known Activations