INDEX

Explanations

mentions related to legal or political issues, such as lawsuits, government actions, and whistleblowing

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

ername

-0.70

sic

-0.70

hene

-0.69

ichick

-0.68

ilon

-0.67

anamo

-0.67

essim

-0.67

etheless

-0.64

warts

-0.64

ilings

-0.63

POSITIVE LOGITS

Description

0.72

Background

0.71

pmwiki

0.70

 Gamer

0.65

Python

0.64

SCP

0.63

Researchers

0.62

ãĥ¤

0.62

Vari

0.61

Sav

0.60

Activations Density 11.992%

mentions related to legal or political issues, such as lawsuits, government actions, and whistleblowing

No Comments

No Known Activations