INDEX

Explanations

terms related to dispatching and/or dispensing various items or information

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

Reviewer

-0.86

Magikarp

-0.74

mingham

-0.68

GER

-0.67

worthy

-0.66

rium

-0.63

HCR

-0.61

sen

-0.61

################

-0.61

ting

-0.60

POSITIVE LOGITS

ersion

0.95

assion

0.91

ossession

0.91

ensed

0.88

atching

0.81

resent

0.80

atches

0.80

 disp

0.80

orter

0.77

lance

0.76

Activations Density 7.324%

terms related to dispatching and/or dispensing various items or information

No Comments

No Known Activations