INDEX

Explanations

situations involving physical actions or conflicts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Soda

-0.73

 Trance

-0.65

Beer

-0.64

ertodd

-0.61

yi

-0.60

 Curve

-0.59

ycle

-0.58

eton

-0.58

atana

-0.57

ÃįÃį

-0.57

POSITIVE LOGITS

 aver

1.04

tle

0.84

ted

0.79

wings

0.78

gets

0.77

ters

0.76

 avert

0.76

ting

0.74

uve

0.72

ultz

0.72

Activations Density 9.429%

situations involving physical actions or conflicts

No Comments

No Known Activations

situations involving physical actions or conflicts

No Comments

No Known Activations