INDEX

Explanations

positive sentiments and expressions of admiration

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

pai

-0.77

gemony

-0.75

eter

-0.75

avis

-0.75

©¶æ

-0.69

eki

-0.65

few

-0.64

resy

-0.63

epend

-0.62

pper

-0.62

POSITIVE LOGITS

 opportunity

0.71

 asset

0.65

 sounding

0.65

 scenery

0.64

NESS

0.64

 synergy

0.64

 example

0.63

 illustrations

0.63

 gift

0.62

 assortment

0.61

Activations Density 11.367%

positive sentiments and expressions of admiration

No Comments

No Known Activations