INDEX

Explanations

the word "lot" followed by various contexts in 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

perty

-0.97

acus

-0.93

ando

-0.92

Constructed

-0.92

ansas

-0.91

heid

-0.89

sburgh

-0.86

agate

-0.84

gary

-0.84

atchewan

-0.83

POSITIVE LOGITS

 amount

0.97

of

0.86

 different

0.85

 nicer

0.81

 bang

0.81

 amounts

0.80

 predictable

0.79

 interesting

0.78

picture

0.78

needed

0.78

Activations Density 4.277%

the word "lot" followed by various contexts in text

No Comments

No Known Activations