INDEX

Explanations

numerical values within text

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

olina

-0.59

fou

-0.59

vier

-0.57

 disg

-0.57

 metast

-0.56

 hump

-0.56

fman

-0.56

yna

-0.56

hyde

-0.56

eros

-0.55

POSITIVE LOGITS

arity

0.60

 Compass

0.56

ADRA

0.54

 Insight

0.54

 Enhancement

0.54

Io

0.53

»Ĵ

0.53

 Parables

0.52

NI

0.51

 Elements

0.51

Activations Density 0.030%

numerical values within text

No Comments

No Known Activations