INDEX

Explanations

terms related to distribution, such as channels, varying distribution, distribution models, and distribution platforms

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

astical

-0.71

uddin

-0.67

glers

-0.67

--+

-0.66

chest

-0.65

ornings

-0.65

itude

-0.64

inx

-0.64

chers

-0.63

aired

-0.62

POSITIVE LOGITS

 distribution

0.90

 Distribution

0.85

eering

0.82

 distribut

0.82

 distributions

0.82

 Distribut

0.81

 distribute

0.77

ally

0.75

 channels

0.73

itarian

0.73

Activations Density 6.807%

terms related to distribution, such as channels, varying distribution, distribution models, and distribution platforms

No Comments

No Known Activations