INDEX

Explanations

references to famous books, fictional characters, and political figures

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

*/(

-0.83

eros

-0.82

uably

-0.81

iasco

-0.76

 Helpful

-0.71

fficient

-0.70

ebin

-0.70

USD

-0.68

arbon

-0.67

ctrl

-0.67

POSITIVE LOGITS

 Admir

0.77

cliffe

0.76

 Sovereign

0.74

 Rothschild

0.74

 Prayer

0.73

 Duchess

0.68

Card

0.67

 Majesty

0.67

assies

0.67

 Lann

0.66

Activations Density 16.550%

references to famous books, fictional characters, and political figures

No Comments

No Known Activations