INDEX

Explanations

phrasal verbs with 'to' and 'have' in the context of instructions or conditions

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

 Majority

-0.69

 Gerard

-0.66

Mit

-0.65

 Impact

-0.65

Hok

-0.63

 Allied

-0.60

 Pompe

-0.60

 Infantry

-0.59

Ang

-0.58

 Vietnam

-0.58

POSITIVE LOGITS

've

1.10

Ĥİ

1.07

'll

1.00

'd

0.99

ldon

0.89

RL

0.87

til

0.86

eding

0.86

're

0.85

eded

0.85

Activations Density 13.016%

phrasal verbs with 'to' and 'have' in the context of instructions or conditions

No Comments

No Known Activations