INDEX

Explanations

proper nouns, specifically names of places, organizations, and individuals

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

enegger

-0.66

HAEL

-0.63

arser

-0.61

avorite

-0.58

lished

-0.57

perty

-0.53

ropolitan

-0.52

 Prospect

-0.51

 sustaining

-0.50

arella

-0.49

POSITIVE LOGITS

gements

0.87

gew

0.86

ged

0.82

uces

0.81

gement

0.80

uction

0.78

der

0.78

gments

0.77

irect

0.75

ging

0.74

Activations Density 9.632%

proper nouns, specifically names of places, organizations, and individuals

No Comments

No Known Activations