INDEX

Explanations

terms related to government, politics, and organizations

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

osity

-0.76

ographs

-0.75

wic

-0.73

ograph

-0.69

 Middles

-0.68

ices

-0.68

Ocean

-0.68

perties

-0.67

fitting

-0.67

ãĤ¹ãĥĪ

-0.67

POSITIVE LOGITS

TF

0.89

PO

0.88

ICLE

0.88

RS

0.87

YL

0.86

OW

0.82

FO

0.81

JA

0.80

MC

0.80

FF

0.80

Activations Density 5.737%

terms related to government, politics, and organizations

No Comments

No Known Activations