INDEX

Explanations

information about products being sold or marketed

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

 Investigations

-0.58

 symmetry

-0.58

issance

-0.55

lihood

-0.54

Nic

-0.48

 Mountains

-0.47

Ago

-0.46

 Relief

-0.45

 Penalty

-0.44

 recourse

-0.44

POSITIVE LOGITS

IER

0.70

ered

0.67

ishing

0.65

Quantity

0.60

Sold

0.60

uca

0.59

iel

0.59

sword

0.58

uer

0.58

cry

0.57

Activations Density 8.132%

information about products being sold or marketed

No Comments

No Known Activations