INDEX

Explanations

references to historical events or significant developments in various fields

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

tics

-0.87

mund

-0.84

gery

-0.79

Ïī

-0.77

crim

-0.70

iety

-0.70

ACTION

-0.70

facing

-0.69

fact

-0.69

politics

-0.69

POSITIVE LOGITS

 baseman

1.13

 responders

1.10

 batch

1.07

 glimpse

0.97

 ever

0.95

 installment

0.93

 foray

0.93

 lady

0.93

 incarnation

0.92

 wave

0.91

Activations Density 8.260%

references to historical events or significant developments in various fields

No Comments

No Known Activations