INDEX

Explanations

dollar amounts and file formats in the 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

]}

-0.70

-0.65

 Nasa

-0.64

²¾

-0.63

neau

-0.63

rir

-0.61

pse

-0.60

ses

-0.59

 contr

-0.57

otics

-0.57

POSITIVE LOGITS

 Located

0.62

vantage

0.59

 Direct

0.59

 Based

0.58

Nit

0.58

advertising

0.58

 Available

0.58

 Express

0.58

iping

0.57

OURCE

0.57

Activations Density 12.487%

dollar amounts and file formats in the text

No Comments

No Known Activations