INDEX

Explanations

mentions of people and military or political activities, possibly related to conflict or controversy

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

catentry

-1.03

inventoryQuantity

-1.03

Smith

-0.84

ICE

-0.82

ory

-0.80

Reloaded

-0.79

Availability

-0.79

POS

-0.78

 Lank

-0.76

 srfAttach

-0.76

POSITIVE LOGITS

hood

1.14

folk

1.10

 smugglers

0.90

ocracy

0.89

atics

0.87

 inhab

0.85

ongs

0.84

 uprising

0.81

 living

0.80

ulkan

0.80

Activations Density 6.293%

mentions of people and military or political activities, possibly related to conflict or controversy

No Comments

No Known Activations