INDEX

Explanations

contradictory statements or opposing viewpoints within a text

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

onomy

-0.71

 Balkans

-0.70

=-=-=-=-=-=-=-=-

-0.69

 labs

-0.67

ted

-0.64

 Annotations

-0.63

burgh

-0.62

anus

-0.62

 laboratories

-0.61

 anth

-0.60

POSITIVE LOGITS

nings

0.85

SPONSORED

0.82

âĶĢâĶĢ

0.76

essage

0.70

invoke

0.68

oths

0.67

 suppose

0.66

è£ħ

0.64

epad

0.64

olphin

0.64

Activations Density 10.455%

contradictory statements or opposing viewpoints within a text

No Comments

No Known Activations