INDEX

Explanations

names of people mentioned in the text or articles

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

į

-1.01

ģĸ

-0.83

berra

-0.80

ãģ®å

-0.80

ãĤµ

-0.78

ĩ

-0.77

 Pixie

-0.74

dyl

-0.74

ãĥīãĥ©ãĤ´ãĥ³

-0.73

ĭ

-0.73

POSITIVE LOGITS

's

0.97

enegger

0.96

gren

0.85

quist

0.85

AFB

0.83

sburg

0.81

enson

0.79

berg

0.77

row

0.75

 wards

0.74

Activations Density 1.569%

names of people mentioned in the text or articles

No Comments

No Known Activations