INDEX

Explanations

information related to surveys and percentages in a text

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

dan

-0.71

kh

-0.66

ington

-0.66

mp

-0.65

Wr

-0.65

amiya

-0.64

 Loft

-0.64

DP

-0.63

ps

-0.62

Mp

-0.62

POSITIVE LOGITS

lamm

0.85

ophysical

0.77

 guiActiveUn

0.72

iosyncr

0.72

escription

0.71

 simulac

0.69

 sclerosis

0.68

utory

0.68

 constitu

0.67

ogeneity

0.67

Activations Density 0.381%

information related to surveys and percentages in a text

No Comments

No Known Activations