INDEX

Explanations

closing actions or events

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥīãĥ©ãĤ´ãĥ³

-0.87

alis

-0.80

ican

-0.79

icist

-0.79

orum

-0.78

nis

-0.76

lain

-0.75

ial

-0.74

cia

-0.73

orius

-0.73

POSITIVE LOGITS

 doors

1.17

 loopholes

1.11

 Doors

1.07

 curtains

1.03

 shutter

0.91

doors

0.90

 door

0.82

 shop

0.81

 throttle

0.81

door

0.80

Activations Density 4.831%

closing actions or events

No Comments

No Known Activations