INDEX

Explanations

references to legal cases, books, and projects for approval

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

NetMessage

-0.75

olulu

-0.73

ãĤ¢ãĥ«

-0.71

Ĭ±

-0.68

azeera

-0.67

othing

-0.67

everal

-0.66

 ILCS

-0.65

 Dhabi

-0.64

ync

-0.63

POSITIVE LOGITS

 itself

1.32

iverse

0.92

wright

0.91

osphere

0.89

maker

0.84

's

0.81

runners

0.79

 revolves

0.78

ultimate

0.77

 yourself

0.76

Activations Density 4.036%

references to legal cases, books, and projects for approval

No Comments

No Known Activations