INDEX

Explanations

verbal threats or negative actions associated with a particular individual

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

bridge

-0.70

thumbnails

-0.67

TAIN

-0.63

starter

-0.61

reflect

-0.60

collar

-0.60

office

-0.60

isSpecialOrderable

-0.59

soon

-0.59

widget

-0.58

POSITIVE LOGITS

 existence

0.64

 heights

0.63

 miracles

0.63

 superiority

0.61

 nostalg

0.59

 immortality

0.59

 excess

0.57

 secrecy

0.57

 perfection

0.57

 tears

0.56

Activations Density 12.648%

verbal threats or negative actions associated with a particular individual

No Comments

No Known Activations