INDEX

Explanations

names containing the substring "Bon"

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

dfx

-0.93

 Ethics

-0.79

UGE

-0.78

ELD

-0.77

gamer

-0.76

INAL

-0.73

 Editorial

-0.72

ODE

-0.70

 Marijuana

-0.69

REAM

-0.69

POSITIVE LOGITS

anza

1.23

iton

1.21

uses

1.10

gey

1.08

itors

1.06

neau

1.06

isson

1.02

etooth

1.02

Bon

1.00

nie

0.99

Activations Density 8.902%

names containing the substring "Bon"

No Comments

No Known Activations