INDEX

Explanations

phrases related to political issues and 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lez

-0.85

minus

-0.78

audi

-0.75

LESS

-0.72

leness

-0.71

Reply

-0.71

osc

-0.69

romy

-0.68

eeee

-0.67

fml

-0.67

POSITIVE LOGITS

piring

1.18

pires

1.02

pects

1.02

 soon

1.01

pired

0.95

piration

0.94

phy

0.93

 evidenced

0.93

 well

0.90

 opposed

0.89

Activations Density 10.967%

phrases related to political issues and events

No Comments

No Known Activations