INDEX

Explanations

political and governmental terms and actions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 hone

-0.66

 setbacks

-0.64

 depiction

-0.63

 depictions

-0.61

 distractions

-0.61

 frustrations

-0.57

 portrayal

-0.57

 uncond

-0.57

effic

-0.57

 inexper

-0.56

POSITIVE LOGITS

ilateral

0.72

 Parliament

0.71

 parliament

0.69

 Select

0.67

 boards

0.67

lder

0.66

 advisory

0.65

ãģ®å®

0.65

 SELECT

0.65

ariat

0.64

Activations Density 12.708%

political and governmental terms and actions

No Comments

No Known Activations