INDEX

Explanations

sentences related to fictional characters, their relationships, and developments in their storylines

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ateur

-0.81

CHAT

-0.78

zanne

-0.75

åĮ

-0.74

Ire

-0.73

ickr

-0.73

 sclerosis

-0.73

TPPStreamerBot

-0.72

 à¤

-0.72

Īè

-0.72

POSITIVE LOGITS

 villains

1.12

canon

1.05

 villain

1.05

buster

1.03

 Deadpool

1.03

 Wolverine

0.97

 Joker

0.95

 Batman

0.94

 Awakens

0.93

 Thunderbolt

0.93

Activations Density 11.894%

sentences related to fictional characters, their relationships, and developments in their storylines

No Comments

No Known Activations