INDEX

Explanations

references to Canon cameras, lenses, and accessories

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

RANT

-0.58

 Antar

-0.57

-+

-0.57

undai

-0.56

 Pupp

-0.56

Frameworks

-0.53

hani

-0.52

pid

-0.52

pants

-0.51

reth

-0.51

POSITIVE LOGITS

icals

1.04

ical

0.96

icles

0.95

icity

0.90

ically

0.89

icle

0.81

ization

0.80

ized

0.76

izations

0.76

ervative

0.71

Activations Density 6.108%

references to Canon cameras, lenses, and accessories

No Comments

No Known Activations