INDEX

Explanations

phrases related to different kinds of slicing or cuts in various contexts

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

rade

-0.71

BAT

-0.71

ians

-0.66

 Hussein

-0.64

raid

-0.64

rouse

-0.63

shire

-0.62

founded

-0.62

ities

-0.61

chemical

-0.59

POSITIVE LOGITS

 slices

1.19

 slice

1.09

 sliced

0.82

slice

0.78

anut

0.77

 slic

0.76

azo

0.75

tery

0.73

meal

0.72

 bread

0.72

Activations Density 7.759%

phrases related to different kinds of slicing or cuts in various contexts

No Comments

No Known Activations