INDEX

Explanations

phrases related to moving forward or progressing

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

©

-0.75

 teasp

-0.72

maximum

-0.70

©¶æ¥µ

-0.69

°

-0.68

MED

-0.65

AMA

-0.65

GV

-0.65

ults

-0.64

ICAN

-0.63

POSITIVE LOGITS

stage

0.93

 stage

0.84

shore

0.81

eday

0.75

 behalf

0.74

topic

0.73

isec

0.73

 toget

0.73

issions

0.73

 bandwagon

0.70

Activations Density 6.813%

phrases related to moving forward or progressing

No Comments

No Known Activations