INDEX

Explanations

text related to historical events

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

 Sparrow

-0.66

 Chero

-0.66

ãģ®å®

-0.63

 Cannon

-0.62

 Dickinson

-0.61

 Shooter

-0.61

Moj

-0.61

 Burr

-0.61

 Hawaiian

-0.60

 Continental

-0.58

POSITIVE LOGITS

morrow

0.90

=-=-=-=-=-=-=-=-

0.89

scale

0.88

advertising

0.88

minded

0.88

mentioned

0.88

camera

0.84

respond

0.83

cause

0.83

yet

0.83

Activations Density 11.836%

text related to historical events

No Comments

No Known Activations

text related to historical events

No Comments

No Known Activations