INDEX

Explanations

words related to decision-making and actions related to decision outcomes

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

soDeliveryDate

-0.65

reports

-0.64

breaks

-0.64

ups

-0.62

fortunately

-0.61

listed

-0.61

 indications

-0.57

ergus

-0.57

cases

-0.57

tips

-0.56

POSITIVE LOGITS

 invoke

1.02

 seek

1.01

 engage

1.00

 maximize

0.98

 communicate

0.95

 promote

0.95

 achieve

0.93

 raise

0.93

 pursue

0.93

 explore

0.92

Activations Density 9.692%

words related to decision-making and actions related to decision outcomes

No Comments

No Known Activations