INDEX

Explanations

references to historical events or locations

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

lain

-1.24

nery

-1.16

gans

-1.01

ullah

-0.96

eret

-0.94

Downloadha

-0.93

wich

-0.87

vae

-0.86

vana

-0.85

ilon

-0.85

POSITIVE LOGITS

orically

1.42

orical

1.25

 significance

1.15

 preservation

1.11

istically

1.10

 accur

1.04

 lows

0.98

arily

0.98

 proportions

0.93

 revision

0.93

Activations Density 1.011%

references to historical events or locations

No Comments

No Known Activations